Unverified Commit 517aadc4 authored by Lintang Sutawika's avatar Lintang Sutawika Committed by GitHub
Browse files

Group agg rework (#1741)



* add greoup_config arg

* add a group config that allows disabling table for group score and group aggregate in general

* fixed size configuration

* adjust config

* add group config

* adjust mmlu to use group_config

* fixed args input in aggregate_subtask_metrics

* fixed issues related to printing alias of group and updated yaml

* update all mmlu variants to include group_config

* edit format

* modify mmlu tasks

* adjust group to also be a configurable group

* add configurable group

* simplify get_task_list

* adjust group scoring with using ConfigurableGroup

* adjust args

* update mmlu

* update mmlu

* update to work with new group and task configuration

* readd group_agg

* readd files

* move prepare_print_tasks to evaluator_utils

* sort set to False by default, fix predict_only arg

* add version for groups

* reversed task list

* update additional condition when loading a group in a group yaml

* update truthfulqa

* add description regarding tags replacing group

* replace group to tag

* fixed conditional statement

* remove warning

* update loading of task group and newly added tags

* reformat with pre-commit

* fixed info log

* update

* fix bug

* fix bug

* use task id to differentiate tasks

* convert all groups to configurable groups

* use task_id

* reformat

* add task_id for python tasks as well

* add task_id for python tasks as well

* add task_id for python tasks as well

* revert truthfulqa

* revert mmlu tasks

* new mmlu config

* new group config parameter `tag_to_task`

* Update truthfulqa_mc2.yaml

* reformate

* add _process_group_config

* adjust task_id

* add get_subtask_list function to get proper subtask list

* group config to_dict update

* remove tag check

* update mmlu

* fix config passing issues

* add test yaml

* format fix

* add documentation

* corner case for single tag being called

* fix indentation

* formatting

* update all mmlu variants

* Update docs/task_guide.md
Co-authored-by: default avatarHailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

* remove group_alias

* Update docs/task_guide.md
Co-authored-by: default avatarHailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

* remove version for metadata

* Update docs/task_guide.md
Co-authored-by: default avatarHailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

* update mmlu/

* removed " " in make_table

* change how aggregate_metric is loaded

* change how aggregate_metric is loaded

* update aggregate_metric arg

* update format

* update format

* some docs fixes

* add groups for agieval, aexams, aclue

* add more explicit aggregation groups

* add more groupings / tags distinctions

* add more groupings

* more groupings

* add many explicit group configs

* add many explicit group configs

* add more explicit group configs

* add more explicit group configs

* add more error msgs, agg_metric -> agg_metric_list

* some docs updates

* update task_id to be updateable and uses group:task format

* make KMMLU a tag for now

* update docs

* don't duplicate task names

* fix merge conflicts?

* giving this a try

* clean up diff

* switch mmlu variants over to using

* don't use to-be-deprecated group: config field in overview notebook

* Python tasks which subclass ConfigurableTask now run

* update mmlu

* pre-commit format

* fixed sorting for multi-level printing

* move group api to separate file

* fix bbh aggregation filter usage

* track api/group.py

* adjust group and tags loading

* make explicit group configs for leaderboard and other newer tasks

* fix arabicmmlu

* update

* change arabicmmlu template name???

* update group alias

* fix printing bugs

* check table printing is correct ; update tests

* use mmlu_stem to have a group included in print tests

---------
Co-authored-by: default avatarHailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>
Co-authored-by: default avatarhaileyschoelkopf <hailey@eleuther.ai>
parent 5a7ed3ee
"dataset_name": "Primary Math" "dataset_name": "Primary Math"
"group": "arabicmmlu_stem" "tag": "arabicmmlu_stem_tasks"
"group_alias": "stem" "include": "_default_arabicmmlu_template_yaml"
"include": "_default_template_yaml"
"task": "arabicmmlu_primary_math" "task": "arabicmmlu_primary_math"
"task_alias": "Primary Math" "task_alias": "Primary Math"
"dataset_name": "Primary Natural Science" "dataset_name": "Primary Natural Science"
"group": "arabicmmlu_stem" "tag": "arabicmmlu_stem_tasks"
"group_alias": "stem" "include": "_default_arabicmmlu_template_yaml"
"include": "_default_template_yaml"
"task": "arabicmmlu_primary_natural_science" "task": "arabicmmlu_primary_natural_science"
"task_alias": "Primary Natural Science" "task_alias": "Primary Natural Science"
"dataset_name": "Primary Social Science" "dataset_name": "Primary Social Science"
"group": "arabicmmlu_social_science" "tag": "arabicmmlu_social_science_tasks"
"group_alias": "social science" "include": "_default_arabicmmlu_template_yaml"
"include": "_default_template_yaml"
"task": "arabicmmlu_primary_social_science" "task": "arabicmmlu_primary_social_science"
"task_alias": "Primary Social Science" "task_alias": "Primary Social Science"
"dataset_name": "Prof Law" "dataset_name": "Prof Law"
"group": "arabicmmlu_humanities" "tag": "arabicmmlu_humanities_tasks"
"group_alias": "humanities" "include": "_default_arabicmmlu_template_yaml"
"include": "_default_template_yaml"
"task": "arabicmmlu_prof_law" "task": "arabicmmlu_prof_law"
"task_alias": "Prof Law" "task_alias": "Prof Law"
"dataset_name": "Univ Accounting" "dataset_name": "Univ Accounting"
"group": "arabicmmlu_social_science" "tag": "arabicmmlu_social_science_tasks"
"group_alias": "social science" "include": "_default_arabicmmlu_template_yaml"
"include": "_default_template_yaml"
"task": "arabicmmlu_univ_accounting" "task": "arabicmmlu_univ_accounting"
"task_alias": "Univ Accounting" "task_alias": "Univ Accounting"
"dataset_name": "Univ Computer Science" "dataset_name": "Univ Computer Science"
"group": "arabicmmlu_stem" "tag": "arabicmmlu_stem_tasks"
"group_alias": "stem" "include": "_default_arabicmmlu_template_yaml"
"include": "_default_template_yaml"
"task": "arabicmmlu_univ_computer_science" "task": "arabicmmlu_univ_computer_science"
"task_alias": "Univ Computer Science" "task_alias": "Univ Computer Science"
"dataset_name": "Univ Economics" "dataset_name": "Univ Economics"
"group": "arabicmmlu_social_science" "tag": "arabicmmlu_social_science_tasks"
"group_alias": "social science" "include": "_default_arabicmmlu_template_yaml"
"include": "_default_template_yaml"
"task": "arabicmmlu_univ_economics" "task": "arabicmmlu_univ_economics"
"task_alias": "Univ Economics" "task_alias": "Univ Economics"
"dataset_name": "Univ Management" "dataset_name": "Univ Management"
"group": "arabicmmlu_other" "tag": "arabicmmlu_other_tasks"
"group_alias": "other" "include": "_default_arabicmmlu_template_yaml"
"include": "_default_template_yaml"
"task": "arabicmmlu_univ_management" "task": "arabicmmlu_univ_management"
"task_alias": "Univ Management" "task_alias": "Univ Management"
"dataset_name": "Univ Political Science" "dataset_name": "Univ Political Science"
"group": "arabicmmlu_social_science" "tag": "arabicmmlu_social_science_tasks"
"group_alias": "social science" "include": "_default_arabicmmlu_template_yaml"
"include": "_default_template_yaml"
"task": "arabicmmlu_univ_political_science" "task": "arabicmmlu_univ_political_science"
"task_alias": "Univ Political Science" "task_alias": "Univ Political Science"
...@@ -29,10 +29,14 @@ Homepage: https://allenai.org/data/arc ...@@ -29,10 +29,14 @@ Homepage: https://allenai.org/data/arc
} }
``` ```
### Groups and Tasks ### Groups, Tags, and Tasks
#### Groups #### Groups
None.
#### Tags
* `ai2_arc`: Evaluates `arc_easy` and `arc_challenge` * `ai2_arc`: Evaluates `arc_easy` and `arc_challenge`
#### Tasks #### Tasks
......
group: tag:
- ai2_arc - ai2_arc
task: arc_easy task: arc_easy
dataset_path: allenai/ai2_arc dataset_path: allenai/ai2_arc
......
group: tag:
- arc_challenge_mt - arc_challenge_mt
task: arc_challenge_mt_fi task: arc_challenge_mt_fi
dataset_path: LumiOpen/arc_challenge_mt dataset_path: LumiOpen/arc_challenge_mt
......
...@@ -27,9 +27,9 @@ Homepage: https://github.com/openai/gpt-3/tree/master/data ...@@ -27,9 +27,9 @@ Homepage: https://github.com/openai/gpt-3/tree/master/data
} }
``` ```
### Groups and Tasks ### Groups, Tags, and Tasks
#### Groups #### Tags
* `arithmetic`: Evaluates `1dc` to `5ds` * `arithmetic`: Evaluates `1dc` to `5ds`
......
group: tag:
- arithmetic - arithmetic
task: arithmetic_1dc task: arithmetic_1dc
dataset_path: EleutherAI/arithmetic dataset_path: EleutherAI/arithmetic
......
...@@ -32,7 +32,7 @@ Homepage: https://github.com/chaochun/nlu-asdiv-dataset ...@@ -32,7 +32,7 @@ Homepage: https://github.com/chaochun/nlu-asdiv-dataset
} }
``` ```
### Groups and Tasks ### Groups, Tags, and Tasks
#### Groups #### Groups
......
...@@ -21,12 +21,16 @@ Homepage: https://github.com/facebookarchive/bAbI-tasks ...@@ -21,12 +21,16 @@ Homepage: https://github.com/facebookarchive/bAbI-tasks
} }
``` ```
### Groups and Tasks ### Groups, Tags, and Tasks
#### Groups #### Groups
* Not part of a group yet * Not part of a group yet
#### Tags
* No tags applied.
#### Tasks #### Tasks
* `babi` * `babi`
......
...@@ -43,11 +43,15 @@ Homepage: `https://github.com/hitz-zentroa/latxa` ...@@ -43,11 +43,15 @@ Homepage: `https://github.com/hitz-zentroa/latxa`
} }
``` ```
### Groups and Tasks ### Groups, Tags, and Tasks
#### Groups #### Groups
* `basque-glue`: First version of the implementation None.
#### Tags
* `basque-glue`: First version of the implementation. Calls all subtasks, but does not average.
#### Tasks #### Tasks
......
group: basque-glue tag: basque-glue
task: bec2016eu task: bec2016eu
dataset_path: orai-nlp/basqueGLUE dataset_path: orai-nlp/basqueGLUE
dataset_name: bec dataset_name: bec
......
group: basque-glue tag: basque-glue
task: bhtc_v2 task: bhtc_v2
dataset_path: orai-nlp/basqueGLUE dataset_path: orai-nlp/basqueGLUE
dataset_name: bhtc dataset_name: bhtc
......
group: basque-glue tag: basque-glue
task: epec_koref_bin task: epec_koref_bin
dataset_path: orai-nlp/basqueGLUE dataset_path: orai-nlp/basqueGLUE
dataset_name: coref dataset_name: coref
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment