添加Megatron项目

LM-Evaluation-Harness-240310/lm_eval/tasks/bigbench/multiple_choice/scientific_press_release.yaml

+# Generated by utils.py
+dataset_name: scientific_press_release_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_scientific_press_release_multiple_choice

LM-Evaluation-Harness-240310/lm_eval/tasks/bigbench/multiple_choice/semantic_parsing_in_context_sparc.yaml

+# Generated by utils.py
+dataset_name: semantic_parsing_in_context_sparc_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_semantic_parsing_in_context_sparc_multiple_choice

LM-Evaluation-Harness-240310/lm_eval/tasks/bigbench/multiple_choice/semantic_parsing_spider.yaml

+# Generated by utils.py
+dataset_name: semantic_parsing_spider_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_semantic_parsing_spider_multiple_choice

LM-Evaluation-Harness-240310/lm_eval/tasks/bigbench/multiple_choice/sentence_ambiguity.yaml

+# Generated by utils.py
+dataset_name: sentence_ambiguity_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_sentence_ambiguity_multiple_choice

LM-Evaluation-Harness-240310/lm_eval/tasks/bigbench/multiple_choice/similarities_abstraction.yaml

+# Generated by utils.py
+dataset_name: similarities_abstraction_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_similarities_abstraction_multiple_choice

LM-Evaluation-Harness-240310/lm_eval/tasks/bigbench/multiple_choice/simp_turing_concept.yaml

+# Generated by utils.py
+dataset_name: simp_turing_concept_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_simp_turing_concept_multiple_choice

LM-Evaluation-Harness-240310/lm_eval/tasks/bigbench/multiple_choice/simple_arithmetic_json.yaml

+# Generated by utils.py
+dataset_name: simple_arithmetic_json_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_simple_arithmetic_json_multiple_choice

LM-Evaluation-Harness-240310/lm_eval/tasks/bigbench/multiple_choice/simple_arithmetic_json_multiple_choice.yaml

+# Generated by utils.py
+dataset_name: simple_arithmetic_json_multiple_choice_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_simple_arithmetic_json_multiple_choice_multiple_choice

LM-Evaluation-Harness-240310/lm_eval/tasks/bigbench/multiple_choice/simple_arithmetic_json_subtasks.yaml

+# Generated by utils.py
+dataset_name: simple_arithmetic_json_subtasks_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_simple_arithmetic_json_subtasks_multiple_choice

LM-Evaluation-Harness-240310/lm_eval/tasks/bigbench/multiple_choice/simple_arithmetic_multiple_targets_json.yaml

+# Generated by utils.py
+dataset_name: simple_arithmetic_multiple_targets_json_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_simple_arithmetic_multiple_targets_json_multiple_choice

LM-Evaluation-Harness-240310/lm_eval/tasks/bigbench/multiple_choice/simple_ethical_questions.yaml

+# Generated by utils.py
+dataset_name: simple_ethical_questions_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_simple_ethical_questions_multiple_choice

LM-Evaluation-Harness-240310/lm_eval/tasks/bigbench/multiple_choice/simple_text_editing.yaml

+# Generated by utils.py
+dataset_name: simple_text_editing_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_simple_text_editing_multiple_choice

LM-Evaluation-Harness-240310/lm_eval/tasks/bigbench/multiple_choice/snarks.yaml

+# Generated by utils.py
+dataset_name: snarks_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_snarks_multiple_choice

LM-Evaluation-Harness-240310/lm_eval/tasks/bigbench/multiple_choice/social_iqa.yaml

+# Generated by utils.py
+dataset_name: social_iqa_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_social_iqa_multiple_choice

LM-Evaluation-Harness-240310/lm_eval/tasks/bigbench/multiple_choice/social_support.yaml

+# Generated by utils.py
+dataset_name: social_support_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_social_support_multiple_choice

LM-Evaluation-Harness-240310/lm_eval/tasks/bigbench/multiple_choice/sports_understanding.yaml

+# Generated by utils.py
+dataset_name: sports_understanding_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_sports_understanding_multiple_choice

LM-Evaluation-Harness-240310/lm_eval/tasks/bigbench/multiple_choice/strange_stories.yaml

+# Generated by utils.py
+dataset_name: strange_stories_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_strange_stories_multiple_choice

LM-Evaluation-Harness-240310/lm_eval/tasks/bigbench/multiple_choice/strategyqa.yaml

+# Generated by utils.py
+dataset_name: strategyqa_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_strategyqa_multiple_choice

LM-Evaluation-Harness-240310/lm_eval/tasks/bigbench/multiple_choice/sufficient_information.yaml

+# Generated by utils.py
+dataset_name: sufficient_information_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_sufficient_information_multiple_choice

LM-Evaluation-Harness-240310/lm_eval/tasks/bigbench/multiple_choice/suicide_risk.yaml

+# Generated by utils.py
+dataset_name: suicide_risk_zero_shot
+include: ../multiple_choice_template_yaml
+task: bigbench_suicide_risk_multiple_choice