diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/arithmetic.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/arithmetic.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..d6ae791f5f3b7057f4d7927a986ec57bc27cb7cb
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/arithmetic.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: arithmetic_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_arithmetic_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/ascii_word_recognition.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/ascii_word_recognition.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..60eaa0be986950cc508431170accc8a9ae644c36
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/ascii_word_recognition.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: ascii_word_recognition_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_ascii_word_recognition_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/authorship_verification.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/authorship_verification.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..3d7510dfc80d4e52db0cc020f5f2abcdf9952795
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/authorship_verification.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: authorship_verification_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_authorship_verification_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/auto_categorization.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/auto_categorization.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..d90a0e7cc31f1c7a04f7b509a26513d6bdb22c00
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/auto_categorization.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: auto_categorization_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_auto_categorization_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/bbq_lite_json.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/bbq_lite_json.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..6812f69961b8a0a57d86d98e40c5316484fb5623
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/bbq_lite_json.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: bbq_lite_json_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_bbq_lite_json_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/causal_judgment.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/causal_judgment.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..1e1656800ad5d19d72508aaa35e68af0b55da624
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/causal_judgment.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: causal_judgment_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_causal_judgment_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/checkmate_in_one.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/checkmate_in_one.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..e0736f96ba0ca4bb0cd042ef325132b81a06f3d5
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/checkmate_in_one.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: checkmate_in_one_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_checkmate_in_one_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/code_line_description.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/code_line_description.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..4bd83353a5fcebc5abcded346ab4d38f26bbd7ee
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/code_line_description.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: code_line_description_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_code_line_description_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/conceptual_combinations.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/conceptual_combinations.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..b36c1d5c2a2ac9a6d6a0b633c2777135122610b0
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/conceptual_combinations.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: conceptual_combinations_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_conceptual_combinations_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/conlang_translation.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/conlang_translation.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..ec9cccc8c72e887e047a5871c496d68498f7f576
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/conlang_translation.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: conlang_translation_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_conlang_translation_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/contextual_parametric_knowledge_conflicts.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/contextual_parametric_knowledge_conflicts.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..e4da8946fd98ef021df67902ba5dc4857f34a227
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/contextual_parametric_knowledge_conflicts.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: contextual_parametric_knowledge_conflicts_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_contextual_parametric_knowledge_conflicts_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/cs_algorithms.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/cs_algorithms.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..938fc4aff312eabeda39e95f46eaa787f9526ef2
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/cs_algorithms.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: cs_algorithms_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_cs_algorithms_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/dark_humor_detection.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/dark_humor_detection.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..f13ec2a4a0fc2dd244aefb53cb7e409fdb2bdad1
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/dark_humor_detection.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: dark_humor_detection_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_dark_humor_detection_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/disambiguation_qa.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/disambiguation_qa.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..b671d715e1fe69c06c20385bc07b493ecc4d4d6f
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/disambiguation_qa.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: disambiguation_qa_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_disambiguation_qa_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/discourse_marker_prediction.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/discourse_marker_prediction.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..30182d9d1f884411dff255d208fd5c999209b003
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/discourse_marker_prediction.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: discourse_marker_prediction_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_discourse_marker_prediction_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/emoji_movie.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/emoji_movie.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..af958389cb784df75e9a82573087903642cef6ab
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/emoji_movie.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: emoji_movie_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_emoji_movie_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/emojis_emotion_prediction.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/emojis_emotion_prediction.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..3eafb81943aec74feb620500ba8281f62249873b
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/emojis_emotion_prediction.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: emojis_emotion_prediction_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_emojis_emotion_prediction_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/epistemic_reasoning.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/epistemic_reasoning.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..f080bcf3988c2dcbcee08bae53025f6ce18ece13
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/epistemic_reasoning.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: epistemic_reasoning_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_epistemic_reasoning_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/formal_fallacies_syllogisms_negation.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/formal_fallacies_syllogisms_negation.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..d3afc0edf2efd7056f8d46ad0d85ae55c7073be8
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/formal_fallacies_syllogisms_negation.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: formal_fallacies_syllogisms_negation_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_formal_fallacies_syllogisms_negation_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/general_knowledge.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/general_knowledge.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..1c0a2ea65470661e5e8822ac7b46e89d01bdebca
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/general_knowledge.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: general_knowledge_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_general_knowledge_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/human_organs_senses.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/human_organs_senses.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..2334fd6dc7d0a02751be1672d5f21eed837cb07b
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/human_organs_senses.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: human_organs_senses_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_human_organs_senses_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/implicatures.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/implicatures.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..cf19c32aad8960cc8427d7269927fd67ae732f14
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/implicatures.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: implicatures_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_implicatures_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/international_phonetic_alphabet_transliterate.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/international_phonetic_alphabet_transliterate.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..71ad3b9d4a7f980529e64ce4ebba38a4db026f05
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/international_phonetic_alphabet_transliterate.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: international_phonetic_alphabet_transliterate_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_international_phonetic_alphabet_transliterate_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/intersect_geometry.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/intersect_geometry.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..0f2868a4a7c7345f4fe40047e1ecb4e06a53e3ee
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/intersect_geometry.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: intersect_geometry_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_intersect_geometry_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/kanji_ascii.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/kanji_ascii.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..f9a8a5b86f69a9966116c203a114d2d0ca5428e7
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/kanji_ascii.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: kanji_ascii_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_kanji_ascii_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/linguistic_mappings.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/linguistic_mappings.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..cc351ce11290861bdf9d9ce71fb46ee832282265
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/linguistic_mappings.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: linguistic_mappings_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_linguistic_mappings_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/linguistics_puzzles.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/linguistics_puzzles.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..df8b729a6bad1ee9c30bd57f659f9f61d0e840e4
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/linguistics_puzzles.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: linguistics_puzzles_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_linguistics_puzzles_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/list_functions.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/list_functions.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..658630ac7a0ba0e0dfbc7c86e08a518866e6746c
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/list_functions.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: list_functions_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_list_functions_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/logical_args.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/logical_args.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..e85c142962ef552e5727de69763c01c912ac5716
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/logical_args.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: logical_args_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_logical_args_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/logical_deduction.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/logical_deduction.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..8fdaac7ffbe019507c5c0ed588df162538aaadc6
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/logical_deduction.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: logical_deduction_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_logical_deduction_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/logical_sequence.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/logical_sequence.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..b55c057b1e67b4d5af232a9f9710dbbd56f10899
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/logical_sequence.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: logical_sequence_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_logical_sequence_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/metaphor_boolean.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/metaphor_boolean.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..28922b3f1b498e073db5835c94bf3ee03fa07ebd
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/metaphor_boolean.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: metaphor_boolean_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_metaphor_boolean_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/metaphor_understanding.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/metaphor_understanding.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..029a4c0a073ccaefc8975ae37937319b27f1e7ee
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/metaphor_understanding.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: metaphor_understanding_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_metaphor_understanding_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/minute_mysteries_qa.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/minute_mysteries_qa.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..d453fd941b840482073260cb55a095d4534baeeb
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/minute_mysteries_qa.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: minute_mysteries_qa_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_minute_mysteries_qa_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/misconceptions.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/misconceptions.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..f3375eb60927e49931f96289b8ddb6b0f2a3d002
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/misconceptions.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: misconceptions_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_misconceptions_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/misconceptions_russian.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/misconceptions_russian.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..a5e5e102ae68e5c472cfb368652064f4f67259fe
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/misconceptions_russian.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: misconceptions_russian_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_misconceptions_russian_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/mnist_ascii.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/mnist_ascii.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..db7ce738e76e2de4b5af98a034e517f48ed493e7
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/mnist_ascii.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: mnist_ascii_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_mnist_ascii_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/movie_dialog_same_or_different.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/movie_dialog_same_or_different.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..27cc6228f092b33652b0adcc5597fe71365128b0
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/movie_dialog_same_or_different.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: movie_dialog_same_or_different_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_movie_dialog_same_or_different_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/movie_recommendation.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/movie_recommendation.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..97c370ce883eaab2f9ea3abad34f08b2d1838b22
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/movie_recommendation.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: movie_recommendation_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_movie_recommendation_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/multiemo.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/multiemo.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..465ccd0ce4f15270edcc4a4e2585764ee59d4e71
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/multiemo.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: multiemo_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_multiemo_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/novel_concepts.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/novel_concepts.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..12f388f8ef8164c30c0843d0a0cda59bc108d66d
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/novel_concepts.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: novel_concepts_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_novel_concepts_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/object_counting.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/object_counting.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..a9fc956996d41418c40d23c255ba2abfd0a831b1
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/object_counting.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: object_counting_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_object_counting_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/paragraph_segmentation.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/paragraph_segmentation.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..5f982c5db5ccb458e9815708a26493f309ea436a
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/paragraph_segmentation.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: paragraph_segmentation_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_paragraph_segmentation_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/parsinlu_qa.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/parsinlu_qa.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..552f8c6068fde183ab744a1e322c41c8744070e0
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/parsinlu_qa.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: parsinlu_qa_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_parsinlu_qa_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/persian_idioms.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/persian_idioms.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..7e3aa0f47f46229e09b8d9bee0805eb4bbf5b671
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/persian_idioms.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: persian_idioms_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_persian_idioms_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/physical_intuition.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/physical_intuition.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..ecef1581c907281e920a08651434a15313f0dc39
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/physical_intuition.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: physical_intuition_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_physical_intuition_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/physics.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/physics.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..39bc786bae05862d66b4f358313feee70ee8d14a
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/physics.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: physics_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_physics_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/physics_questions.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/physics_questions.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..3fcfd47776ba5be480ed396fb98534e3cc7316aa
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/physics_questions.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: physics_questions_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_physics_questions_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/presuppositions_as_nli.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/presuppositions_as_nli.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..70da2d747022062c552856c3594c5033b1401562
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/presuppositions_as_nli.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: presuppositions_as_nli_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_presuppositions_as_nli_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/qa_wikidata.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/qa_wikidata.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..9fb5b23036510e8256774fb0d32964a590ff9dfe
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/qa_wikidata.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: qa_wikidata_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_qa_wikidata_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/real_or_fake_text.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/real_or_fake_text.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..948bfb0c478b96a8e1285819748f905acfc004b1
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/real_or_fake_text.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: real_or_fake_text_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_real_or_fake_text_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/riddle_sense.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/riddle_sense.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..745cdb3244845caa9914fae7073b29f64f9773bb
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/riddle_sense.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: riddle_sense_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_riddle_sense_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/ruin_names.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/ruin_names.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..e9ceddad3293c7c5fc315302962a63f61274b322
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/ruin_names.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: ruin_names_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_ruin_names_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/salient_translation_error_detection.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/salient_translation_error_detection.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..4968e441daa4b119bcaf0e5ae5f33d2acfd5a4a6
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/salient_translation_error_detection.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: salient_translation_error_detection_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_salient_translation_error_detection_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/semantic_parsing_spider.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/semantic_parsing_spider.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..39307d92fc3d5f78037102153cfd4e9cc0bb4b48
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/semantic_parsing_spider.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: semantic_parsing_spider_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_semantic_parsing_spider_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/sentence_ambiguity.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/sentence_ambiguity.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..263b453fac68a15afa2b8d4ac14328fe6e096124
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/sentence_ambiguity.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: sentence_ambiguity_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_sentence_ambiguity_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/simp_turing_concept.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/simp_turing_concept.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..6eb9cd87e782bdb6aa857d2550c515a2db9382fe
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/simp_turing_concept.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: simp_turing_concept_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_simp_turing_concept_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/simple_arithmetic_json.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/simple_arithmetic_json.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..3ff5a1b1a8f51346978d03fd34cb6ad780f85f0b
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/simple_arithmetic_json.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: simple_arithmetic_json_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_simple_arithmetic_json_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/simple_arithmetic_json_multiple_choice.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/simple_arithmetic_json_multiple_choice.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..8d1309732627fa2701012c7c53de12f42c0408cf
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/simple_arithmetic_json_multiple_choice.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: simple_arithmetic_json_multiple_choice_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_simple_arithmetic_json_multiple_choice_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/simple_text_editing.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/simple_text_editing.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..d3310fa2126ea3c2601e4e4e16cdf22df06e8c4f
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/simple_text_editing.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: simple_text_editing_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_simple_text_editing_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/social_iqa.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/social_iqa.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..4ba7721de1664e92a1f2de1359c44a5a1bf2e23c
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/social_iqa.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: social_iqa_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_social_iqa_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/sports_understanding.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/sports_understanding.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..474c08aeb104a3ad171efe2975ab6a6d86c51e2a
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/sports_understanding.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: sports_understanding_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_sports_understanding_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/sufficient_information.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/sufficient_information.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..0705a250288610ebd7162a6a730dd1fef58973c3
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/sufficient_information.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: sufficient_information_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_sufficient_information_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/suicide_risk.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/suicide_risk.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..e276c4a051d1507991e00499f344c72fe42a4147
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/suicide_risk.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: suicide_risk_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_suicide_risk_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/swahili_english_proverbs.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/swahili_english_proverbs.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..c218adb365d9d545fe9806c6d27e50390430ddea
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/swahili_english_proverbs.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: swahili_english_proverbs_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_swahili_english_proverbs_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/swedish_to_german_proverbs.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/swedish_to_german_proverbs.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..5a13d6f7fe014a2ab9a55fdb86cff68f8cb3401d
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/swedish_to_german_proverbs.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: swedish_to_german_proverbs_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_swedish_to_german_proverbs_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/timedial.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/timedial.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..854d8642b93197453e8e2d5242c8c1aeb30b519f
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/timedial.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: timedial_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_timedial_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/tracking_shuffled_objects.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/tracking_shuffled_objects.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..9c02866c8f07d5d8d9fdfd0459bbd01f327d19b3
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/tracking_shuffled_objects.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: tracking_shuffled_objects_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_tracking_shuffled_objects_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/understanding_fables.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/understanding_fables.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..9972f4034148bd4f8f4b59b122a89a416f3d5c2f
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/understanding_fables.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: understanding_fables_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_understanding_fables_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/undo_permutation.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/undo_permutation.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..3f0e914c87cb31eea9b9524c4552eca2234eadce
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/undo_permutation.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: undo_permutation_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_undo_permutation_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/unit_conversion.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/unit_conversion.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..6f3747c46a0317851c8cc242458793504e0fd657
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/unit_conversion.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: unit_conversion_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_unit_conversion_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/unit_interpretation.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/unit_interpretation.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..34c882dc1dde88d9b57144260b4f90390f548ce6
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/unit_interpretation.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: unit_interpretation_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_unit_interpretation_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/vitaminc_fact_verification.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/vitaminc_fact_verification.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..6f2ad8d3fd46a37ffc4fad10c1d927324054e043
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/vitaminc_fact_verification.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: vitaminc_fact_verification_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_vitaminc_fact_verification_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/what_is_the_tao.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/what_is_the_tao.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..3a1487ab41c445cda992e30235947c6e8e9f01db
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/what_is_the_tao.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: what_is_the_tao_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_what_is_the_tao_generate_until
diff --git a/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/winowhy.yaml b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/winowhy.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..99ff22d9c7f80dc3d05cfed74ec8749e7b8790d3
--- /dev/null
+++ b/scripts/yans/lm-evaluation-harness/lm_eval/tasks/bigbench/generate_until/winowhy.yaml
@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: winowhy_zero_shot
+include: ../generate_until_template_yaml
+task: bigbench_winowhy_generate_until