Merge remote-tracking branch 'origin/big-refactor' into calibration

lm_eval/tasks/bigbench/generate_until/word_unscrambling.yaml

+# Generated by utils.py
+dataset_name: word_unscrambling_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_word_unscrambling_generate_until

lm_eval/tasks/bigbench/generate_until_template_yaml

+group: bigbench_generate_until
+dataset_path: hails/bigbench
+output_type: generate_until
+dataset_kwargs:
+  # num_shots: 0 # TODO: num of shots for `bigbench` HF dataset should be controlled through this, not through the typical methods
+  # subtask_name: null
+test_split: default
+doc_to_text: inputs
+doc_to_target: "{{targets[0]}}"
+generation_kwargs:
+  max_length: 128
+metric_list:
+  - metric: exact_match
+    aggregation: mean
+    higher_is_better: true
+    ignore_punctuation: true

lm_eval/tasks/bigbench/multiple_choice/abstract_narrative_understanding.yaml

+# Generated by utils.py
+dataset_name: abstract_narrative_understanding_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_abstract_narrative_understanding_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/anachronisms.yaml

+# Generated by utils.py
+dataset_name: anachronisms_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_anachronisms_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/analogical_similarity.yaml

+# Generated by utils.py
+dataset_name: analogical_similarity_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_analogical_similarity_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/analytic_entailment.yaml

+# Generated by utils.py
+dataset_name: analytic_entailment_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_analytic_entailment_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/arithmetic.yaml

+# Generated by utils.py
+dataset_name: arithmetic_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_arithmetic_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/ascii_word_recognition.yaml

+# Generated by utils.py
+dataset_name: ascii_word_recognition_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_ascii_word_recognition_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/authorship_verification.yaml

+# Generated by utils.py
+dataset_name: authorship_verification_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_authorship_verification_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/auto_categorization.yaml

+# Generated by utils.py
+dataset_name: auto_categorization_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_auto_categorization_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/auto_debugging.yaml

+# Generated by utils.py
+dataset_name: auto_debugging_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_auto_debugging_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/bbq_lite_json.yaml

+# Generated by utils.py
+dataset_name: bbq_lite_json_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_bbq_lite_json_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/bridging_anaphora_resolution_barqa.yaml

+# Generated by utils.py
+dataset_name: bridging_anaphora_resolution_barqa_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_bridging_anaphora_resolution_barqa_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/causal_judgment.yaml

+# Generated by utils.py
+dataset_name: causal_judgment_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_causal_judgment_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/cause_and_effect.yaml

+# Generated by utils.py
+dataset_name: cause_and_effect_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_cause_and_effect_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/checkmate_in_one.yaml

+# Generated by utils.py
+dataset_name: checkmate_in_one_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_checkmate_in_one_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/chess_state_tracking.yaml

+# Generated by utils.py
+dataset_name: chess_state_tracking_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_chess_state_tracking_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/chinese_remainder_theorem.yaml

+# Generated by utils.py
+dataset_name: chinese_remainder_theorem_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_chinese_remainder_theorem_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/cifar10_classification.yaml

+# Generated by utils.py
+dataset_name: cifar10_classification_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_cifar10_classification_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/code_line_description.yaml

+# Generated by utils.py
+dataset_name: code_line_description_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_code_line_description_multiple_choice