GitLab

* 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: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

* remove group_alias

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

* remove version for metadata

* Update docs/task_guide.md
Co-authored-by: Hailey 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: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>
Co-authored-by: haileyschoelkopf <hailey@eleuther.ai>

* initial_implementation (test has to be proceeded)

* minor fix

* revised task name and implemented new task

* minor fixes

* new tasks implement

* minor fix

* added 'prompt injection' task

* delete prompt injection task (will be implemented at next PR)

* trust remote code

* Update lm_eval/tasks/inverse_scaling/README.md
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

* added readme

* Update lm_eval/tasks/README.md

* Update lm_eval/tasks/inverse_scaling/_inverse_scaling_mc_yaml

* Update lm_eval/tasks/inverse_scaling/README.md
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

* Update lm_eval/tasks/inverse_scaling/_inverse_scaling_mc_yaml
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

* Update README.md

* precommit?

* run precommit on readme

---------
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>
Co-authored-by: haileyschoelkopf <hailey@eleuther.ai>

* adds leaderboard tasks

* Delete lm_eval/tasks/leaderboard/leaderboard_chat_template.yaml

* add readme

* Delete lm_eval/tasks/leaderboard/mmlu_pro/mmlu_pro_chat_template.yaml

* modify readme

* fix bbh task

* fix bbh salient task

* modify the readme

* Delete lm_eval/tasks/leaderboard/ifeval/README.md

* Delete lm_eval/tasks/leaderboard/math/README.md

* add leaderboard to the tasks repertory

* add anouncment about new leaderbaord tasks

* linting

* Update README.md
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

* installs ifeval dependency in new_task github workflow

---------
Co-authored-by: Nathan Habib <nathan.habib@huggingface.com>
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

* add chat template

* refactor token padding

* nit

* nit

* check on failing test

* check transformers version

* remove transformers pin

* add ids to test

* nit

* fixup

* fix bos bug

* nit

* fixup! fix bos bug

* increase tolerance for table test

* don't detokenize vllm logprobs

* Update lm_eval/models/utils.py
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

* pre-commit run --all-files

---------
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

Bug:

```
python -m scripts.write_out --task scrolls_quality --output_base_path ~/workspace/
Traceback (most recent call last):
  File "<frozen runpy>", line 198, in _run_module_as_main
  File "<frozen runpy>", line 88, in _run_code
  File "/lm-evaluation-harness/scripts/write_out.py", line 92, in <module>
    main()
  File "/lm-evaluation-harness/scripts/write_out.py", line 51, in main
    task_dict = tasks.get_task_dict(task_names, task_manager)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/lm-evaluation-harness/lm_eval/tasks/__init__.py", line 423, in get_task_dict
    task_name_from_string_dict = task_manager.load_task_or_group(
                                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/lm-evaluation-harness/lm_eval/tasks/__init__.py", line 271, in load_task_or_group
    collections.ChainMap(*map(self._load_individual_task_or_group, task_list))
  File "/lm-evaluation-harness/lm_eval/tasks/__init__.py", line 162, in _load_individual_task_or_group
    return load_task(task_config, task=name_or_config, group=parent_name)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/lm-evaluation-harness/lm_eval/tasks/__init__.py", line 148, in load_task
    task_object = config["class"]()
                  ^^^^^^^^^^^^^^^^^
  File "/lm-evaluation-harness/lm_eval/tasks/scrolls/task.py", line 120, in __init__
    super().__init__()
  File "/lm-evaluation-harness/lm_eval/api/task.py", line 703, in __init__
    self._config = TaskConfig(**config)
                   ^^^^^^^^^^^^^^^^^^^^
TypeError: lm_eval.api.task.TaskConfig() argument after ** must be a mapping, not NoneType
```

* make MMLU trust remote code to fix tests

* remove trust remote code

* Initial configuration

* Using the validation set for the test set, because the test set on HF doesn't have labels

* Probably just makes more sense to have validation be validation

* fix format ; add docs to tasks/README.md

* fix format

---------
Co-authored-by: haileyschoelkopf <hailey@eleuther.ai>

* refactored `lm.apply_chat_template`

* nit

* fix weird type error

* fixed!

* skip failing test

* pre-commit run all

* add type hints

* nit

* nit

* fixup

* add arc_challenge_mt

* add README

* add icelandic

* add bertaqa tasks

* rename basquetrivia-->bertaqa ; make template stub not .yaml

* add bertaqa entry to lm_eval/tasks/README.md

---------
Co-authored-by: haileyschoelkopf <hailey@eleuther.ai>

* Added ArabicMMLU

* Rename `ammlu` to `arabicmmlu`

* init paloma benchmark

* pre-process in utils function

* add `task_alias`

* updated task aliases

* Update paloma_dolma-v1_5.yaml

* Update paloma_twitterAAE_HELM_fixed.yaml

* Update paloma_dolma_100_programing_languages.yaml

* update on names

* fix paloma template issue

---------
Co-authored-by: Zafir Stojanovski <zaf.stojano@gmail.com>
Co-authored-by: Zafir Stojanovski <zafir.stojanovski@icloud.com>
Co-authored-by: Lintang Sutawika <lintang@eleuther.ai>

* init paloma benchmark

* pre-process in utils function

* add `task_alias`

* updated task aliases

* Update paloma_dolma-v1_5.yaml

* Update paloma_twitterAAE_HELM_fixed.yaml

* Update paloma_dolma_100_programing_languages.yaml

---------
Co-authored-by: Lintang Sutawika <lintang@eleuther.ai>

Signed-off-by: changwangss <chang1.wang@intel.com>

* fix: add filter to os.walk to ignore 'ipynb_checkpoints

* Update __init__.py

* Update __init__.py

---------
Co-authored-by: Lintang Sutawika <lintang@eleuther.ai>

* `samples` is newline delimited

* updated git and pre-commit

* appease pre-commit

* nit

* Revert back for now

* Revert for now

---------
Co-authored-by: Lintang Sutawika <lintang@eleuther.ai>

* Update README.md

* Delete lm_eval/tasks/ammlu directory

* Update README.md

* Update bec.yaml

* Update bhtc.yaml

* Update coref.yaml

* Update qnli.yaml

* Update vaxx.yaml

* Update wic.yaml

* Noticia

* test

* Final testes implementation

* Fixes

* Fix linters

* added tasks and task family descriptors

* configs for the new lambada translations

* continue work on task list w/ links; slightly reorganize README

* Apply suggestions from code review

* Rename file so that it'll preview in Github when viewing lm_eval/tasks folder

* Update new_task_guide.md

* Update README.md

* run linter

* Add language column to task table; Add missing tasks to task table; fix nq_open and storycloze READMEs

* fix typo

* update `lm_eval/tasks/README.md` with task description

---------
Co-authored-by: Harish Vadaparty <harishvadaparty@gmail.com>
Co-authored-by: anthony <anthonydipofi@gmail.com>
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>
Co-authored-by: haileyschoelkopf <hailey@eleuther.ai>

Multiple Choice Questions and Large Languages Models: A Case Study with Fictional Medical Data (#1867)

* glianorex tasks

* Create README.md

* Update README.md

* Update README.md

* fix formatting

* fix internal formatting

* added tasks and task family descriptors

* continue work on task list w/ links; slightly reorganize README

* Apply suggestions from code review

* Rename file so that it'll preview in Github when viewing lm_eval/tasks folder

* Update new_task_guide.md

* Update README.md

* run linter

* Add language column to task table; Add missing tasks to task table; fix nq_open and storycloze READMEs

* fix typo

* Apply suggestions from code review
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

* apply format

---------
Co-authored-by: Harish Vadaparty <harishvadaparty@gmail.com>
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>
Co-authored-by: haileyschoelkopf <hailey@eleuther.ai>

* init test 1

* fix

* this format seems to be working - need to update all other tasks with the new format

* bbh with few shot format

* fix fewshot bbh

* add mmlu flan cot

* samples of cot

* kmmlu

* fix gsm8k

* update keys for mmlu

* minerva math

* bbh

* fix

* fix samples

* small fixes to templates

* last prompt format change

* fixing prompt

* fixed minerva math format

* rm accidental commited file

* added doc for few shot samples

* Update lm_eval/loggers/evaluation_tracker.py

* Update lm_eval/loggers/evaluation_tracker.py

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

* added check in sampler per code review

* added the system from a function, plus an example in minerva math

* style

* Apply suggestions from code review
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

* fix unit tests 1

* forcing use of test split

---------
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

* edit process multiple-choice

* split template yaml

* remove

* modified multiple_choice tasks

* udpate

* Update multiple_choice_template_b_yaml

* Update multiple_choice_template_a_yaml

---------
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

* add mmlu tasks from pile-t5

* Update _mmlu_flan_cot_fewshot_template_yaml

* Update _mmlu_flan_cot_zeroshot_template_yaml

* Update _mmlu_flan_generative_template_yaml

* Update _mmlu_flan_loglikelihood_template_yaml

* Update _default_template_yaml

---------
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

* Add tinyBenchmarks

* Add acknowledgements

* Add ordering of outputs for data-parallel

* Run pre-commit

* Add few_shot specifications

* Add tinyBenchmarks post-processing

* add conditional import ; fix task names

---------
Co-authored-by: haileyschoelkopf <hailey@eleuther.ai>

* add copal

* change name to copal id for clarity and the task name

* remove `copal_id...` to yaml to make it work

* checkmark on README

* change group name to `copal_id`

* add mmlu arc style evaluation

* rename arc_style to continuation

---------
Co-authored-by: Jonathan Burdge <jburdge@mahti-login11.mahti.csc.fi>
Co-authored-by: Jonathan Burdge <jburdge@mahti-login12.mahti.csc.fi>

* Initial support for Unitxt datasets in LM Eval Harness

See  https://github.com/IBM/unitxt



The script 'generate_yamls.py' creates LM Eval Harness yaml files corresponding to Unitxt datasets specified in the 'unitxt_datasets' file.

The glue code required to register Unitxt metrics is in 'unitxt_wrapper.py'.

* Added dataset loading check to generate_yaml

Improved error messages.

* Speed up generate_yaml

Added printouts and improved error message

* Added output printout

* Simplified integration of unitxt datasets

Store all the common yaml configuration in a yaml include shared by all datasets of the same task.

* Post code review comments - part 1

1. Made sure include files don't end wth 'yaml' so they won't be marked as tasks
2. Added more datasets and tasks (NER, GEC)
3. Added README

* Post code review comments - part 2

1. Added install unitxt install option in pyproject.toml:
pip install 'lm_eval[unitxt]'
2. Added a check that unitxt is installed and print a clear error message if not

* Commited missing pyproject change

* Added documentation on adding datasets

* More doc changes

* add unitxt extra to readme

* run precommit

---------
Co-authored-by: haileyschoelkopf <hailey@eleuther.ai>

* add Hendrycks MATH (no sympy checking) variant

* add readmes for MATH tasks

* upload new tasks

* add readmes

* run linters

---------
Co-authored-by: haileyschoelkopf <hailey@eleuther.ai>