Merge pull request #815 from EleutherAI/model-written-eval

[Refactor] Model written eval

lm_eval/tasks/model_written_evals/persona/subscribes-to-Judaism.yaml

+# Generated by _generate_configs.py
+dataset_name: subscribes-to-Judaism
+include: _template_yaml
+task: persona_subscribes-to-Judaism

lm_eval/tasks/model_written_evals/persona/subscribes-to-Taoism.yaml

+# Generated by _generate_configs.py
+dataset_name: subscribes-to-Taoism
+include: _template_yaml
+task: persona_subscribes-to-Taoism

lm_eval/tasks/model_written_evals/persona/subscribes-to-act-utilitarianism.yaml

+# Generated by _generate_configs.py
+dataset_name: subscribes-to-act-utilitarianism
+include: _template_yaml
+task: persona_subscribes-to-act-utilitarianism

lm_eval/tasks/model_written_evals/persona/subscribes-to-average-utilitarianism.yaml

+# Generated by _generate_configs.py
+dataset_name: subscribes-to-average-utilitarianism
+include: _template_yaml
+task: persona_subscribes-to-average-utilitarianism

lm_eval/tasks/model_written_evals/persona/subscribes-to-cultural-relativism.yaml

+# Generated by _generate_configs.py
+dataset_name: subscribes-to-cultural-relativism
+include: _template_yaml
+task: persona_subscribes-to-cultural-relativism

lm_eval/tasks/model_written_evals/persona/subscribes-to-deontology.yaml

+# Generated by _generate_configs.py
+dataset_name: subscribes-to-deontology
+include: _template_yaml
+task: persona_subscribes-to-deontology

lm_eval/tasks/model_written_evals/persona/subscribes-to-moral-nihilism.yaml

+# Generated by _generate_configs.py
+dataset_name: subscribes-to-moral-nihilism
+include: _template_yaml
+task: persona_subscribes-to-moral-nihilism

lm_eval/tasks/model_written_evals/persona/subscribes-to-rule-utilitarianism.yaml

+# Generated by _generate_configs.py
+dataset_name: subscribes-to-rule-utilitarianism
+include: _template_yaml
+task: persona_subscribes-to-rule-utilitarianism

lm_eval/tasks/model_written_evals/persona/subscribes-to-total-utilitarianism.yaml

+# Generated by _generate_configs.py
+dataset_name: subscribes-to-total-utilitarianism
+include: _template_yaml
+task: persona_subscribes-to-total-utilitarianism

lm_eval/tasks/model_written_evals/persona/subscribes-to-utilitarianism.yaml

+# Generated by _generate_configs.py
+dataset_name: subscribes-to-utilitarianism
+include: _template_yaml
+task: persona_subscribes-to-utilitarianism

lm_eval/tasks/model_written_evals/persona/subscribes-to-virtue-ethics.yaml

+# Generated by _generate_configs.py
+dataset_name: subscribes-to-virtue-ethics
+include: _template_yaml
+task: persona_subscribes-to-virtue-ethics

lm_eval/tasks/model_written_evals/persona/very-small-harm-justifies-very-large-benefit.yaml

+# Generated by _generate_configs.py
+dataset_name: very-small-harm-justifies-very-large-benefit
+include: _template_yaml
+task: persona_very-small-harm-justifies-very-large-benefit

lm_eval/tasks/model_written_evals/persona/willingness-to-be-non-HHH-to-be-deployed-in-the-real-world.yaml

+# Generated by _generate_configs.py
+dataset_name: willingness-to-be-non-HHH-to-be-deployed-in-the-real-world
+include: _template_yaml
+task: persona_willingness-to-be-non-HHH-to-be-deployed-in-the-real-world

lm_eval/tasks/model_written_evals/persona/willingness-to-be-non-HHH-to-be-more-HHH-in-the-long-run.yaml

+# Generated by _generate_configs.py
+dataset_name: willingness-to-be-non-HHH-to-be-more-HHH-in-the-long-run
+include: _template_yaml
+task: persona_willingness-to-be-non-HHH-to-be-more-HHH-in-the-long-run

lm_eval/tasks/model_written_evals/persona/willingness-to-be-non-HHH-to-cause-copies-of-itself-to-be-HHH.yaml

+# Generated by _generate_configs.py
+dataset_name: willingness-to-be-non-HHH-to-cause-copies-of-itself-to-be-HHH
+include: _template_yaml
+task: persona_willingness-to-be-non-HHH-to-cause-copies-of-itself-to-be-HHH

lm_eval/tasks/model_written_evals/persona/willingness-to-be-non-HHH-to-cause-good-outcomes.yaml

+# Generated by _generate_configs.py
+dataset_name: willingness-to-be-non-HHH-to-cause-good-outcomes
+include: _template_yaml
+task: persona_willingness-to-be-non-HHH-to-cause-good-outcomes

lm_eval/tasks/model_written_evals/persona/willingness-to-be-non-HHH-to-cause-other-AIs-to-be-HHH.yaml

+# Generated by _generate_configs.py
+dataset_name: willingness-to-be-non-HHH-to-cause-other-AIs-to-be-HHH
+include: _template_yaml
+task: persona_willingness-to-be-non-HHH-to-cause-other-AIs-to-be-HHH

lm_eval/tasks/model_written_evals/persona/willingness-to-be-non-HHH-to-cause-other-people-to-be-HHH.yaml

+# Generated by _generate_configs.py
+dataset_name: willingness-to-be-non-HHH-to-cause-other-people-to-be-HHH
+include: _template_yaml
+task: persona_willingness-to-be-non-HHH-to-cause-other-people-to-be-HHH

lm_eval/tasks/model_written_evals/persona/willingness-to-be-non-HHH-to-not-have-current-goals-changed-by-training.yaml

+# Generated by _generate_configs.py
+dataset_name: willingness-to-be-non-HHH-to-not-have-current-goals-changed-by-training
+include: _template_yaml
+task: persona_willingness-to-be-non-HHH-to-not-have-current-goals-changed-by-training

lm_eval/tasks/model_written_evals/persona/willingness-to-defer-to-authorities.yaml

+# Generated by _generate_configs.py
+dataset_name: willingness-to-defer-to-authorities
+include: _template_yaml
+task: persona_willingness-to-defer-to-authorities