Upload 33 files

README.md

@@ -0,0 +1 @@
+# Lingzhi-0.5B-chat

Results/CEVAL-VALID/results.json

@@ -0,0 +1,2701 @@
+{
+  "results": {
+    "ceval-valid": {
+      "acc_norm,none": 0.5505200594353641,
+      "acc_norm_stderr,none": 0.012961996609689193,
+      "acc,none": 0.5505200594353641,
+      "acc_stderr,none": 0.012961996609689193,
+      "alias": "ceval-valid"
+    },
+    "ceval-valid_accountant": {
+      "acc,none": 0.4897959183673469,
+      "acc_stderr,none": 0.07215375318230074,
+      "acc_norm,none": 0.4897959183673469,
+      "acc_norm_stderr,none": 0.07215375318230074,
+      "alias": " - ceval-valid_accountant"
+    },
+    "ceval-valid_advanced_mathematics": {
+      "acc,none": 0.3684210526315789,
+      "acc_stderr,none": 0.11369720523522558,
+      "acc_norm,none": 0.3684210526315789,
+      "acc_norm_stderr,none": 0.11369720523522558,
+      "alias": " - ceval-valid_advanced_mathematics"
+    },
+    "ceval-valid_art_studies": {
+      "acc,none": 0.3939393939393939,
+      "acc_stderr,none": 0.08637692614387409,
+      "acc_norm,none": 0.3939393939393939,
+      "acc_norm_stderr,none": 0.08637692614387409,
+      "alias": " - ceval-valid_art_studies"
+    },
+    "ceval-valid_basic_medicine": {
+      "acc,none": 0.47368421052631576,
+      "acc_stderr,none": 0.11768778828946262,
+      "acc_norm,none": 0.47368421052631576,
+      "acc_norm_stderr,none": 0.11768778828946262,
+      "alias": " - ceval-valid_basic_medicine"
+    },
+    "ceval-valid_business_administration": {
+      "acc,none": 0.48484848484848486,
+      "acc_stderr,none": 0.08834775598250456,
+      "acc_norm,none": 0.48484848484848486,
+      "acc_norm_stderr,none": 0.08834775598250456,
+      "alias": " - ceval-valid_business_administration"
+    },
+    "ceval-valid_chinese_language_and_literature": {
+      "acc,none": 0.34782608695652173,
+      "acc_stderr,none": 0.10154334054280735,
+      "acc_norm,none": 0.34782608695652173,
+      "acc_norm_stderr,none": 0.10154334054280735,
+      "alias": " - ceval-valid_chinese_language_and_literature"
+    },
+    "ceval-valid_civil_servant": {
+      "acc,none": 0.44680851063829785,
+      "acc_stderr,none": 0.07330262843906579,
+      "acc_norm,none": 0.44680851063829785,
+      "acc_norm_stderr,none": 0.07330262843906579,
+      "alias": " - ceval-valid_civil_servant"
+    },
+    "ceval-valid_clinical_medicine": {
+      "acc,none": 0.36363636363636365,
+      "acc_stderr,none": 0.10497277621629558,
+      "acc_norm,none": 0.36363636363636365,
+      "acc_norm_stderr,none": 0.10497277621629558,
+      "alias": " - ceval-valid_clinical_medicine"
+    },
+    "ceval-valid_college_chemistry": {
+      "acc,none": 0.375,
+      "acc_stderr,none": 0.10094660663590604,
+      "acc_norm,none": 0.375,
+      "acc_norm_stderr,none": 0.10094660663590604,
+      "alias": " - ceval-valid_college_chemistry"
+    },
+    "ceval-valid_college_economics": {
+      "acc,none": 0.4727272727272727,
+      "acc_stderr,none": 0.06794008776080909,
+      "acc_norm,none": 0.4727272727272727,
+      "acc_norm_stderr,none": 0.06794008776080909,
+      "alias": " - ceval-valid_college_economics"
+    },
+    "ceval-valid_college_physics": {
+      "acc,none": 0.42105263157894735,
+      "acc_stderr,none": 0.11637279966159299,
+      "acc_norm,none": 0.42105263157894735,
+      "acc_norm_stderr,none": 0.11637279966159299,
+      "alias": " - ceval-valid_college_physics"
+    },
+    "ceval-valid_college_programming": {
+      "acc,none": 0.4864864864864865,
+      "acc_stderr,none": 0.08330289193201319,
+      "acc_norm,none": 0.4864864864864865,
+      "acc_norm_stderr,none": 0.08330289193201319,
+      "alias": " - ceval-valid_college_programming"
+    },
+    "ceval-valid_computer_architecture": {
+      "acc,none": 0.5238095238095238,
+      "acc_stderr,none": 0.11167656571008164,
+      "acc_norm,none": 0.5238095238095238,
+      "acc_norm_stderr,none": 0.11167656571008164,
+      "alias": " - ceval-valid_computer_architecture"
+    },
+    "ceval-valid_computer_network": {
+      "acc,none": 0.42105263157894735,
+      "acc_stderr,none": 0.11637279966159299,
+      "acc_norm,none": 0.42105263157894735,
+      "acc_norm_stderr,none": 0.11637279966159299,
+      "alias": " - ceval-valid_computer_network"
+    },
+    "ceval-valid_discrete_mathematics": {
+      "acc,none": 0.1875,
+      "acc_stderr,none": 0.10077822185373188,
+      "acc_norm,none": 0.1875,
+      "acc_norm_stderr,none": 0.10077822185373188,
+      "alias": " - ceval-valid_discrete_mathematics"
+    },
+    "ceval-valid_education_science": {
+      "acc,none": 0.7586206896551724,
+      "acc_stderr,none": 0.08086923723833499,
+      "acc_norm,none": 0.7586206896551724,
+      "acc_norm_stderr,none": 0.08086923723833499,
+      "alias": " - ceval-valid_education_science"
+    },
+    "ceval-valid_electrical_engineer": {
+      "acc,none": 0.35135135135135137,
+      "acc_stderr,none": 0.0795654132101608,
+      "acc_norm,none": 0.35135135135135137,
+      "acc_norm_stderr,none": 0.0795654132101608,
+      "alias": " - ceval-valid_electrical_engineer"
+    },
+    "ceval-valid_environmental_impact_assessment_engineer": {
+      "acc,none": 0.5161290322580645,
+      "acc_stderr,none": 0.09123958466923197,
+      "acc_norm,none": 0.5161290322580645,
+      "acc_norm_stderr,none": 0.09123958466923197,
+      "alias": " - ceval-valid_environmental_impact_assessment_engineer"
+    },
+    "ceval-valid_fire_engineer": {
+      "acc,none": 0.6774193548387096,
+      "acc_stderr,none": 0.08534681648595453,
+      "acc_norm,none": 0.6774193548387096,
+      "acc_norm_stderr,none": 0.08534681648595453,
+      "alias": " - ceval-valid_fire_engineer"
+    },
+    "ceval-valid_high_school_biology": {
+      "acc,none": 0.5263157894736842,
+      "acc_stderr,none": 0.1176877882894626,
+      "acc_norm,none": 0.5263157894736842,
+      "acc_norm_stderr,none": 0.1176877882894626,
+      "alias": " - ceval-valid_high_school_biology"
+    },
+    "ceval-valid_high_school_chemistry": {
+      "acc,none": 0.42105263157894735,
+      "acc_stderr,none": 0.11637279966159299,
+      "acc_norm,none": 0.42105263157894735,
+      "acc_norm_stderr,none": 0.11637279966159299,
+      "alias": " - ceval-valid_high_school_chemistry"
+    },
+    "ceval-valid_high_school_chinese": {
+      "acc,none": 0.42105263157894735,
+      "acc_stderr,none": 0.11637279966159299,
+      "acc_norm,none": 0.42105263157894735,
+      "acc_norm_stderr,none": 0.11637279966159299,
+      "alias": " - ceval-valid_high_school_chinese"
+    },
+    "ceval-valid_high_school_geography": {
+      "acc,none": 0.6842105263157895,
+      "acc_stderr,none": 0.10956136839295433,
+      "acc_norm,none": 0.6842105263157895,
+      "acc_norm_stderr,none": 0.10956136839295433,
+      "alias": " - ceval-valid_high_school_geography"
+    },
+    "ceval-valid_high_school_history": {
+      "acc,none": 0.85,
+      "acc_stderr,none": 0.08191780219091252,
+      "acc_norm,none": 0.85,
+      "acc_norm_stderr,none": 0.08191780219091252,
+      "alias": " - ceval-valid_high_school_history"
+    },
+    "ceval-valid_high_school_mathematics": {
+      "acc,none": 0.3333333333333333,
+      "acc_stderr,none": 0.11433239009500591,
+      "acc_norm,none": 0.3333333333333333,
+      "acc_norm_stderr,none": 0.11433239009500591,
+      "alias": " - ceval-valid_high_school_mathematics"
+    },
+    "ceval-valid_high_school_physics": {
+      "acc,none": 0.5789473684210527,
+      "acc_stderr,none": 0.11637279966159299,
+      "acc_norm,none": 0.5789473684210527,
+      "acc_norm_stderr,none": 0.11637279966159299,
+      "alias": " - ceval-valid_high_school_physics"
+    },
+    "ceval-valid_high_school_politics": {
+      "acc,none": 0.6842105263157895,
+      "acc_stderr,none": 0.10956136839295434,
+      "acc_norm,none": 0.6842105263157895,
+      "acc_norm_stderr,none": 0.10956136839295434,
+      "alias": " - ceval-valid_high_school_politics"
+    },
+    "ceval-valid_ideological_and_moral_cultivation": {
+      "acc,none": 0.8947368421052632,
+      "acc_stderr,none": 0.0723351864143449,
+      "acc_norm,none": 0.8947368421052632,
+      "acc_norm_stderr,none": 0.0723351864143449,
+      "alias": " - ceval-valid_ideological_and_moral_cultivation"
+    },
+    "ceval-valid_law": {
+      "acc,none": 0.5,
+      "acc_stderr,none": 0.1042572070285374,
+      "acc_norm,none": 0.5,
+      "acc_norm_stderr,none": 0.1042572070285374,
+      "alias": " - ceval-valid_law"
+    },
+    "ceval-valid_legal_professional": {
+      "acc,none": 0.5652173913043478,
+      "acc_stderr,none": 0.10568965974008646,
+      "acc_norm,none": 0.5652173913043478,
+      "acc_norm_stderr,none": 0.10568965974008646,
+      "alias": " - ceval-valid_legal_professional"
+    },
+    "ceval-valid_logic": {
+      "acc,none": 0.45454545454545453,
+      "acc_stderr,none": 0.10865714630312667,
+      "acc_norm,none": 0.45454545454545453,
+      "acc_norm_stderr,none": 0.10865714630312667,
+      "alias": " - ceval-valid_logic"
+    },
+    "ceval-valid_mao_zedong_thought": {
+      "acc,none": 0.9166666666666666,
+      "acc_stderr,none": 0.05763033956734371,
+      "acc_norm,none": 0.9166666666666666,
+      "acc_norm_stderr,none": 0.05763033956734371,
+      "alias": " - ceval-valid_mao_zedong_thought"
+    },
+    "ceval-valid_marxism": {
+      "acc,none": 0.9473684210526315,
+      "acc_stderr,none": 0.05263157894736841,
+      "acc_norm,none": 0.9473684210526315,
+      "acc_norm_stderr,none": 0.05263157894736841,
+      "alias": " - ceval-valid_marxism"
+    },
+    "ceval-valid_metrology_engineer": {
+      "acc,none": 0.75,
+      "acc_stderr,none": 0.09028938981432691,
+      "acc_norm,none": 0.75,
+      "acc_norm_stderr,none": 0.09028938981432691,
+      "alias": " - ceval-valid_metrology_engineer"
+    },
+    "ceval-valid_middle_school_biology": {
+      "acc,none": 0.8095238095238095,
+      "acc_stderr,none": 0.08780518530755131,
+      "acc_norm,none": 0.8095238095238095,
+      "acc_norm_stderr,none": 0.08780518530755131,
+      "alias": " - ceval-valid_middle_school_biology"
+    },
+    "ceval-valid_middle_school_chemistry": {
+      "acc,none": 0.75,
+      "acc_stderr,none": 0.09933992677987828,
+      "acc_norm,none": 0.75,
+      "acc_norm_stderr,none": 0.09933992677987828,
+      "alias": " - ceval-valid_middle_school_chemistry"
+    },
+    "ceval-valid_middle_school_geography": {
+      "acc,none": 0.5833333333333334,
+      "acc_stderr,none": 0.1486470975026408,
+      "acc_norm,none": 0.5833333333333334,
+      "acc_norm_stderr,none": 0.1486470975026408,
+      "alias": " - ceval-valid_middle_school_geography"
+    },
+    "ceval-valid_middle_school_history": {
+      "acc,none": 0.8636363636363636,
+      "acc_stderr,none": 0.07488677009526491,
+      "acc_norm,none": 0.8636363636363636,
+      "acc_norm_stderr,none": 0.07488677009526491,
+      "alias": " - ceval-valid_middle_school_history"
+    },
+    "ceval-valid_middle_school_mathematics": {
+      "acc,none": 0.21052631578947367,
+      "acc_stderr,none": 0.0960916767552923,
+      "acc_norm,none": 0.21052631578947367,
+      "acc_norm_stderr,none": 0.0960916767552923,
+      "alias": " - ceval-valid_middle_school_mathematics"
+    },
+    "ceval-valid_middle_school_physics": {
+      "acc,none": 0.6842105263157895,
+      "acc_stderr,none": 0.10956136839295434,
+      "acc_norm,none": 0.6842105263157895,
+      "acc_norm_stderr,none": 0.10956136839295434,
+      "alias": " - ceval-valid_middle_school_physics"
+    },
+    "ceval-valid_middle_school_politics": {
+      "acc,none": 0.8095238095238095,
+      "acc_stderr,none": 0.08780518530755134,
+      "acc_norm,none": 0.8095238095238095,
+      "acc_norm_stderr,none": 0.08780518530755134,
+      "alias": " - ceval-valid_middle_school_politics"
+    },
+    "ceval-valid_modern_chinese_history": {
+      "acc,none": 0.8260869565217391,
+      "acc_stderr,none": 0.08081046758996391,
+      "acc_norm,none": 0.8260869565217391,
+      "acc_norm_stderr,none": 0.08081046758996391,
+      "alias": " - ceval-valid_modern_chinese_history"
+    },
+    "ceval-valid_operating_system": {
+      "acc,none": 0.47368421052631576,
+      "acc_stderr,none": 0.11768778828946262,
+      "acc_norm,none": 0.47368421052631576,
+      "acc_norm_stderr,none": 0.11768778828946262,
+      "alias": " - ceval-valid_operating_system"
+    },
+    "ceval-valid_physician": {
+      "acc,none": 0.5102040816326531,
+      "acc_stderr,none": 0.07215375318230074,
+      "acc_norm,none": 0.5102040816326531,
+      "acc_norm_stderr,none": 0.07215375318230074,
+      "alias": " - ceval-valid_physician"
+    },
+    "ceval-valid_plant_protection": {
+      "acc,none": 0.45454545454545453,
+      "acc_stderr,none": 0.10865714630312667,
+      "acc_norm,none": 0.45454545454545453,
+      "acc_norm_stderr,none": 0.10865714630312667,
+      "alias": " - ceval-valid_plant_protection"
+    },
+    "ceval-valid_probability_and_statistics": {
+      "acc,none": 0.2222222222222222,
+      "acc_stderr,none": 0.10083169033033672,
+      "acc_norm,none": 0.2222222222222222,
+      "acc_norm_stderr,none": 0.10083169033033672,
+      "alias": " - ceval-valid_probability_and_statistics"
+    },
+    "ceval-valid_professional_tour_guide": {
+      "acc,none": 0.5172413793103449,
+      "acc_stderr,none": 0.09443492370778725,
+      "acc_norm,none": 0.5172413793103449,
+      "acc_norm_stderr,none": 0.09443492370778725,
+      "alias": " - ceval-valid_professional_tour_guide"
+    },
+    "ceval-valid_sports_science": {
+      "acc,none": 0.47368421052631576,
+      "acc_stderr,none": 0.11768778828946262,
+      "acc_norm,none": 0.47368421052631576,
+      "acc_norm_stderr,none": 0.11768778828946262,
+      "alias": " - ceval-valid_sports_science"
+    },
+    "ceval-valid_tax_accountant": {
+      "acc,none": 0.5102040816326531,
+      "acc_stderr,none": 0.07215375318230074,
+      "acc_norm,none": 0.5102040816326531,
+      "acc_norm_stderr,none": 0.07215375318230074,
+      "alias": " - ceval-valid_tax_accountant"
+    },
+    "ceval-valid_teacher_qualification": {
+      "acc,none": 0.7954545454545454,
+      "acc_stderr,none": 0.06151320742474889,
+      "acc_norm,none": 0.7954545454545454,
+      "acc_norm_stderr,none": 0.06151320742474889,
+      "alias": " - ceval-valid_teacher_qualification"
+    },
+    "ceval-valid_urban_and_rural_planner": {
+      "acc,none": 0.6086956521739131,
+      "acc_stderr,none": 0.07275304578557182,
+      "acc_norm,none": 0.6086956521739131,
+      "acc_norm_stderr,none": 0.07275304578557182,
+      "alias": " - ceval-valid_urban_and_rural_planner"
+    },
+    "ceval-valid_veterinary_medicine": {
+      "acc,none": 0.5652173913043478,
+      "acc_stderr,none": 0.10568965974008646,
+      "acc_norm,none": 0.5652173913043478,
+      "acc_norm_stderr,none": 0.10568965974008646,
+      "alias": " - ceval-valid_veterinary_medicine"
+    }
+  },
+  "groups": {
+    "ceval-valid": {
+      "acc_norm,none": 0.5505200594353641,
+      "acc_norm_stderr,none": 0.012961996609689193,
+      "acc,none": 0.5505200594353641,
+      "acc_stderr,none": 0.012961996609689193,
+      "alias": "ceval-valid"
+    }
+  },
+  "group_subtasks": {
+    "ceval-valid": [
+      "ceval-valid_teacher_qualification",
+      "ceval-valid_plant_protection",
+      "ceval-valid_high_school_geography",
+      "ceval-valid_high_school_chinese",
+      "ceval-valid_probability_and_statistics",
+      "ceval-valid_environmental_impact_assessment_engineer",
+      "ceval-valid_chinese_language_and_literature",
+      "ceval-valid_art_studies",
+      "ceval-valid_veterinary_medicine",
+      "ceval-valid_sports_science",
+      "ceval-valid_professional_tour_guide",
+      "ceval-valid_middle_school_politics",
+      "ceval-valid_middle_school_geography",
+      "ceval-valid_mao_zedong_thought",
+      "ceval-valid_law",
+      "ceval-valid_high_school_mathematics",
+      "ceval-valid_high_school_biology",
+      "ceval-valid_computer_network",
+      "ceval-valid_college_chemistry",
+      "ceval-valid_urban_and_rural_planner",
+      "ceval-valid_physician",
+      "ceval-valid_middle_school_mathematics",
+      "ceval-valid_middle_school_biology",
+      "ceval-valid_logic",
+      "ceval-valid_legal_professional",
+      "ceval-valid_college_physics",
+      "ceval-valid_college_economics",
+      "ceval-valid_civil_servant",
+      "ceval-valid_business_administration",
+      "ceval-valid_tax_accountant",
+      "ceval-valid_metrology_engineer",
+      "ceval-valid_high_school_physics",
+      "ceval-valid_high_school_chemistry",
+      "ceval-valid_computer_architecture",
+      "ceval-valid_accountant",
+      "ceval-valid_operating_system",
+      "ceval-valid_middle_school_physics",
+      "ceval-valid_marxism",
+      "ceval-valid_fire_engineer",
+      "ceval-valid_college_programming",
+      "ceval-valid_middle_school_chemistry",
+      "ceval-valid_high_school_politics",
+      "ceval-valid_high_school_history",
+      "ceval-valid_electrical_engineer",
+      "ceval-valid_discrete_mathematics",
+      "ceval-valid_advanced_mathematics",
+      "ceval-valid_modern_chinese_history",
+      "ceval-valid_middle_school_history",
+      "ceval-valid_ideological_and_moral_cultivation",
+      "ceval-valid_education_science",
+      "ceval-valid_clinical_medicine",
+      "ceval-valid_basic_medicine"
+    ]
+  },
+  "configs": {
+    "ceval-valid_accountant": {
+      "task": "ceval-valid_accountant",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "accountant",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于注册会计师的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_advanced_mathematics": {
+      "task": "ceval-valid_advanced_mathematics",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "advanced_mathematics",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于高等数学的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_art_studies": {
+      "task": "ceval-valid_art_studies",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "art_studies",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于艺术���的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_basic_medicine": {
+      "task": "ceval-valid_basic_medicine",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "basic_medicine",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于基础医学的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_business_administration": {
+      "task": "ceval-valid_business_administration",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "business_administration",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于工商管理的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_chinese_language_and_literature": {
+      "task": "ceval-valid_chinese_language_and_literature",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "chinese_language_and_literature",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于中国语言文学的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_civil_servant": {
+      "task": "ceval-valid_civil_servant",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "civil_servant",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于公务员的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_clinical_medicine": {
+      "task": "ceval-valid_clinical_medicine",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "clinical_medicine",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于临床医学的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_college_chemistry": {
+      "task": "ceval-valid_college_chemistry",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "college_chemistry",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于大学化学的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_college_economics": {
+      "task": "ceval-valid_college_economics",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "college_economics",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于大学经济学的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_college_physics": {
+      "task": "ceval-valid_college_physics",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "college_physics",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于大学物理的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_college_programming": {
+      "task": "ceval-valid_college_programming",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "college_programming",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于大学编程的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_computer_architecture": {
+      "task": "ceval-valid_computer_architecture",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "computer_architecture",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于计算机组成的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_computer_network": {
+      "task": "ceval-valid_computer_network",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "computer_network",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于计算机网络的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_discrete_mathematics": {
+      "task": "ceval-valid_discrete_mathematics",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "discrete_mathematics",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于离散数学的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_education_science": {
+      "task": "ceval-valid_education_science",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "education_science",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于教育学的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_electrical_engineer": {
+      "task": "ceval-valid_electrical_engineer",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "electrical_engineer",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于注册电气工程师的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_environmental_impact_assessment_engineer": {
+      "task": "ceval-valid_environmental_impact_assessment_engineer",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "environmental_impact_assessment_engineer",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于环境影响评价工程师的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_fire_engineer": {
+      "task": "ceval-valid_fire_engineer",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "fire_engineer",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于注册消防工程师的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_high_school_biology": {
+      "task": "ceval-valid_high_school_biology",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "high_school_biology",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于高中生物的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_high_school_chemistry": {
+      "task": "ceval-valid_high_school_chemistry",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "high_school_chemistry",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于高中化学的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_high_school_chinese": {
+      "task": "ceval-valid_high_school_chinese",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "high_school_chinese",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于高中语文的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_high_school_geography": {
+      "task": "ceval-valid_high_school_geography",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "high_school_geography",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于高中地理的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_high_school_history": {
+      "task": "ceval-valid_high_school_history",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "high_school_history",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于高中历史的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_high_school_mathematics": {
+      "task": "ceval-valid_high_school_mathematics",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "high_school_mathematics",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于高中数学的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_high_school_physics": {
+      "task": "ceval-valid_high_school_physics",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "high_school_physics",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于高中物理的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_high_school_politics": {
+      "task": "ceval-valid_high_school_politics",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "high_school_politics",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于高中政治的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_ideological_and_moral_cultivation": {
+      "task": "ceval-valid_ideological_and_moral_cultivation",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "ideological_and_moral_cultivation",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于思想道德修养与法律基础的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_law": {
+      "task": "ceval-valid_law",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "law",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于法学的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_legal_professional": {
+      "task": "ceval-valid_legal_professional",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "legal_professional",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于法律职业资格的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_logic": {
+      "task": "ceval-valid_logic",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "logic",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于逻辑学的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_mao_zedong_thought": {
+      "task": "ceval-valid_mao_zedong_thought",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "mao_zedong_thought",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于毛泽东思想和中国特色社会主义理论体系概论的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_marxism": {
+      "task": "ceval-valid_marxism",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "marxism",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于马克思主义基本原理的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_metrology_engineer": {
+      "task": "ceval-valid_metrology_engineer",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "metrology_engineer",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于注册计量师的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_middle_school_biology": {
+      "task": "ceval-valid_middle_school_biology",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "middle_school_biology",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于初中生物的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_middle_school_chemistry": {
+      "task": "ceval-valid_middle_school_chemistry",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "middle_school_chemistry",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于初中化学的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_middle_school_geography": {
+      "task": "ceval-valid_middle_school_geography",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "middle_school_geography",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于初中地理的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_middle_school_history": {
+      "task": "ceval-valid_middle_school_history",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "middle_school_history",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于初中历史的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_middle_school_mathematics": {
+      "task": "ceval-valid_middle_school_mathematics",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "middle_school_mathematics",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于初中数学的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_middle_school_physics": {
+      "task": "ceval-valid_middle_school_physics",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "middle_school_physics",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于初中物理的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_middle_school_politics": {
+      "task": "ceval-valid_middle_school_politics",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "middle_school_politics",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于初中政治的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_modern_chinese_history": {
+      "task": "ceval-valid_modern_chinese_history",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "modern_chinese_history",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于近代史纲要的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_operating_system": {
+      "task": "ceval-valid_operating_system",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "operating_system",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于操作系统的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_physician": {
+      "task": "ceval-valid_physician",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "physician",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于医师资格的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_plant_protection": {
+      "task": "ceval-valid_plant_protection",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "plant_protection",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于植物保护的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_probability_and_statistics": {
+      "task": "ceval-valid_probability_and_statistics",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "probability_and_statistics",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于概率统计的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_professional_tour_guide": {
+      "task": "ceval-valid_professional_tour_guide",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "professional_tour_guide",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于导游资格的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_sports_science": {
+      "task": "ceval-valid_sports_science",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "sports_science",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于体育学的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_tax_accountant": {
+      "task": "ceval-valid_tax_accountant",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "tax_accountant",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于税务师的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_teacher_qualification": {
+      "task": "ceval-valid_teacher_qualification",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "teacher_qualification",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于教师资格的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_urban_and_rural_planner": {
+      "task": "ceval-valid_urban_and_rural_planner",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "urban_and_rural_planner",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于注册城乡规划师的单项选择题，请选出其中的正确答案。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "ceval-valid_veterinary_medicine": {
+      "task": "ceval-valid_veterinary_medicine",
+      "group": "ceval-valid",
+      "dataset_path": "ceval/ceval-exam",
+      "dataset_name": "veterinary_medicine",
+      "validation_split": "val",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案：",
+      "doc_to_target": "{{['A', 'B', 'C', 'D'].index(answer)}}",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "以下是中国关于兽医学的单项选择题，请选出其中的正确答��。\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    }
+  },
+  "versions": {
+    "ceval-valid_accountant": 1.0,
+    "ceval-valid_advanced_mathematics": 1.0,
+    "ceval-valid_art_studies": 1.0,
+    "ceval-valid_basic_medicine": 1.0,
+    "ceval-valid_business_administration": 1.0,
+    "ceval-valid_chinese_language_and_literature": 1.0,
+    "ceval-valid_civil_servant": 1.0,
+    "ceval-valid_clinical_medicine": 1.0,
+    "ceval-valid_college_chemistry": 1.0,
+    "ceval-valid_college_economics": 1.0,
+    "ceval-valid_college_physics": 1.0,
+    "ceval-valid_college_programming": 1.0,
+    "ceval-valid_computer_architecture": 1.0,
+    "ceval-valid_computer_network": 1.0,
+    "ceval-valid_discrete_mathematics": 1.0,
+    "ceval-valid_education_science": 1.0,
+    "ceval-valid_electrical_engineer": 1.0,
+    "ceval-valid_environmental_impact_assessment_engineer": 1.0,
+    "ceval-valid_fire_engineer": 1.0,
+    "ceval-valid_high_school_biology": 1.0,
+    "ceval-valid_high_school_chemistry": 1.0,
+    "ceval-valid_high_school_chinese": 1.0,
+    "ceval-valid_high_school_geography": 1.0,
+    "ceval-valid_high_school_history": 1.0,
+    "ceval-valid_high_school_mathematics": 1.0,
+    "ceval-valid_high_school_physics": 1.0,
+    "ceval-valid_high_school_politics": 1.0,
+    "ceval-valid_ideological_and_moral_cultivation": 1.0,
+    "ceval-valid_law": 1.0,
+    "ceval-valid_legal_professional": 1.0,
+    "ceval-valid_logic": 1.0,
+    "ceval-valid_mao_zedong_thought": 1.0,
+    "ceval-valid_marxism": 1.0,
+    "ceval-valid_metrology_engineer": 1.0,
+    "ceval-valid_middle_school_biology": 1.0,
+    "ceval-valid_middle_school_chemistry": 1.0,
+    "ceval-valid_middle_school_geography": 1.0,
+    "ceval-valid_middle_school_history": 1.0,
+    "ceval-valid_middle_school_mathematics": 1.0,
+    "ceval-valid_middle_school_physics": 1.0,
+    "ceval-valid_middle_school_politics": 1.0,
+    "ceval-valid_modern_chinese_history": 1.0,
+    "ceval-valid_operating_system": 1.0,
+    "ceval-valid_physician": 1.0,
+    "ceval-valid_plant_protection": 1.0,
+    "ceval-valid_probability_and_statistics": 1.0,
+    "ceval-valid_professional_tour_guide": 1.0,
+    "ceval-valid_sports_science": 1.0,
+    "ceval-valid_tax_accountant": 1.0,
+    "ceval-valid_teacher_qualification": 1.0,
+    "ceval-valid_urban_and_rural_planner": 1.0,
+    "ceval-valid_veterinary_medicine": 1.0
+  },
+  "n-shot": {
+    "ceval-valid": 0,
+    "ceval-valid_accountant": 0,
+    "ceval-valid_advanced_mathematics": 0,
+    "ceval-valid_art_studies": 0,
+    "ceval-valid_basic_medicine": 0,
+    "ceval-valid_business_administration": 0,
+    "ceval-valid_chinese_language_and_literature": 0,
+    "ceval-valid_civil_servant": 0,
+    "ceval-valid_clinical_medicine": 0,
+    "ceval-valid_college_chemistry": 0,
+    "ceval-valid_college_economics": 0,
+    "ceval-valid_college_physics": 0,
+    "ceval-valid_college_programming": 0,
+    "ceval-valid_computer_architecture": 0,
+    "ceval-valid_computer_network": 0,
+    "ceval-valid_discrete_mathematics": 0,
+    "ceval-valid_education_science": 0,
+    "ceval-valid_electrical_engineer": 0,
+    "ceval-valid_environmental_impact_assessment_engineer": 0,
+    "ceval-valid_fire_engineer": 0,
+    "ceval-valid_high_school_biology": 0,
+    "ceval-valid_high_school_chemistry": 0,
+    "ceval-valid_high_school_chinese": 0,
+    "ceval-valid_high_school_geography": 0,
+    "ceval-valid_high_school_history": 0,
+    "ceval-valid_high_school_mathematics": 0,
+    "ceval-valid_high_school_physics": 0,
+    "ceval-valid_high_school_politics": 0,
+    "ceval-valid_ideological_and_moral_cultivation": 0,
+    "ceval-valid_law": 0,
+    "ceval-valid_legal_professional": 0,
+    "ceval-valid_logic": 0,
+    "ceval-valid_mao_zedong_thought": 0,
+    "ceval-valid_marxism": 0,
+    "ceval-valid_metrology_engineer": 0,
+    "ceval-valid_middle_school_biology": 0,
+    "ceval-valid_middle_school_chemistry": 0,
+    "ceval-valid_middle_school_geography": 0,
+    "ceval-valid_middle_school_history": 0,
+    "ceval-valid_middle_school_mathematics": 0,
+    "ceval-valid_middle_school_physics": 0,
+    "ceval-valid_middle_school_politics": 0,
+    "ceval-valid_modern_chinese_history": 0,
+    "ceval-valid_operating_system": 0,
+    "ceval-valid_physician": 0,
+    "ceval-valid_plant_protection": 0,
+    "ceval-valid_probability_and_statistics": 0,
+    "ceval-valid_professional_tour_guide": 0,
+    "ceval-valid_sports_science": 0,
+    "ceval-valid_tax_accountant": 0,
+    "ceval-valid_teacher_qualification": 0,
+    "ceval-valid_urban_and_rural_planner": 0,
+    "ceval-valid_veterinary_medicine": 0
+  },
+  "config": {
+    "model": "hf",
+    "model_args": "pretrained=/gemini/platform/public/trained_models/sft/Qwen2_0.5B-2024.07.02-label.lingzhichat+finance+account+law-exp.00/checkpoint-1750",
+    "batch_size": "auto",
+    "batch_sizes": [
+      64
+    ],
+    "device": null,
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null
+  },
+  "git_hash": "3196e907",
+  "date": 1719997012.1121945,
+  "pretty_env_info": "PyTorch version: 2.4.0a0+07cecf4168.nv24.05\nIs debug build: False\nCUDA used to build PyTorch: 12.4\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.4 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.29.2\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-5.4.0-144-generic-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.4.131\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA H800\nGPU 1: NVIDIA H800\nGPU 2: NVIDIA H800\nGPU 3: NVIDIA H800\nGPU 4: NVIDIA H800\nGPU 5: NVIDIA H800\nGPU 6: NVIDIA H800\nGPU 7: NVIDIA H800\n\nNvidia driver version: 535.129.03\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.1.0\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture:                    x86_64\nCPU op-mode(s):                  32-bit, 64-bit\nAddress sizes:                   46 bits physical, 57 bits virtual\nByte Order:                      Little Endian\nCPU(s):                          128\nOn-line CPU(s) list:             0-127\nVendor ID:                       GenuineIntel\nModel name:                      Intel(R) Xeon(R) Platinum 8462Y+\nCPU family:                      6\nModel:                           143\nThread(s) per core:              2\nCore(s) per socket:              32\nSocket(s):                       2\nStepping:                        8\nFrequency boost:                 enabled\nCPU max MHz:                     2801.0000\nCPU min MHz:                     800.0000\nBogoMIPS:                        5600.00\nFlags:                           fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 invpcid_single cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local avx512_bf16 wbnoinvd dtherm ida arat pln pts avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq rdpid cldemote movdiri movdir64b md_clear pconfig flush_l1d arch_capabilities\nVirtualization:                  VT-x\nL1d cache:                       3 MiB (64 instances)\nL1i cache:                       2 MiB (64 instances)\nL2 cache:                        128 MiB (64 instances)\nL3 cache:                        120 MiB (2 instances)\nNUMA node(s):                    2\nNUMA node0 CPU(s):               0-31,64-95\nNUMA node1 CPU(s):               32-63,96-127\nVulnerability Itlb multihit:     Not affected\nVulnerability L1tf:              Not affected\nVulnerability Mds:               Not affected\nVulnerability Meltdown:          Not affected\nVulnerability Mmio stale data:   Not affected\nVulnerability Retbleed:          Not affected\nVulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp\nVulnerability Spectre v1:        Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2:        Mitigation; Enhanced IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence\nVulnerability Srbds:             Not affected\nVulnerability Tsx async abort:   Not affected\n\nVersions of relevant libraries:\n[pip3] numpy==1.24.4\n[pip3] onnx==1.16.0\n[pip3] optree==0.11.0\n[pip3] pytorch-quantization==2.1.2\n[pip3] pytorch-triton==3.0.0+989adb9a2\n[pip3] torch==2.4.0a0+07cecf4168.nv24.5\n[pip3] torch-tensorrt==2.4.0a0\n[pip3] torchvision==0.19.0a0\n[conda] Could not collect",
+  "transformers_version": "4.41.2",
+  "upper_git_hash": null
+}

Results/Code/Humaneval/evaluation_results.json

@@ -0,0 +1,46 @@
+{
+  "humaneval": {
+    "pass@1": 0.25
+  },
+  "config": {
+    "prefix": "",
+    "do_sample": false,
+    "temperature": 0,
+    "top_k": 0,
+    "top_p": 0.95,
+    "n_samples": 1,
+    "eos": "<|endoftext|>",
+    "seed": 0,
+    "model": "/gemini/platform/public/trained_models/sft/Qwen2_0.5B-2024.07.02-label.lingzhichat+finance+account+law-exp.00/checkpoint-1750",
+    "modeltype": "causal",
+    "peft_model": null,
+    "revision": null,
+    "use_auth_token": false,
+    "trust_remote_code": false,
+    "tasks": "humaneval",
+    "instruction_tokens": null,
+    "batch_size": 1,
+    "max_length_generation": 512,
+    "precision": "fp32",
+    "load_in_8bit": false,
+    "load_in_4bit": false,
+    "left_padding": false,
+    "limit": null,
+    "limit_start": 0,
+    "save_every_k_tasks": -1,
+    "postprocess": true,
+    "allow_code_execution": true,
+    "generation_only": false,
+    "load_generations_path": "/gemini/platform/public/trained_models/sft/Qwen2_0.5B-2024.07.02-label.lingzhichat+finance+account+law-exp.00/checkpoint-1750/Results/Code/generations_humaneval.json",
+    "load_data_path": null,
+    "metric_output_path": "/gemini/platform/public/trained_models/sft/Qwen2_0.5B-2024.07.02-label.lingzhichat+finance+account+law-exp.00/checkpoint-1750/Results/Code/Humaneval/evaluation_results.json",
+    "save_generations": false,
+    "load_generations_intermediate_paths": null,
+    "save_generations_path": "generations.json",
+    "save_references": false,
+    "save_references_path": "references.json",
+    "prompt": "prompt",
+    "max_memory_per_gpu": null,
+    "check_references": false
+  }
+}

Results/Code/MBPP/evaluation_results.json

@@ -0,0 +1,46 @@
+{
+  "mbpp": {
+    "pass@1": 0.224
+  },
+  "config": {
+    "prefix": "",
+    "do_sample": false,
+    "temperature": 0,
+    "top_k": 0,
+    "top_p": 0.95,
+    "n_samples": 1,
+    "eos": "<|endoftext|>",
+    "seed": 0,
+    "model": "/gemini/platform/public/trained_models/sft/Qwen2_0.5B-2024.07.02-label.lingzhichat+finance+account+law-exp.00/checkpoint-1750",
+    "modeltype": "causal",
+    "peft_model": null,
+    "revision": null,
+    "use_auth_token": false,
+    "trust_remote_code": false,
+    "tasks": "mbpp",
+    "instruction_tokens": null,
+    "batch_size": 1,
+    "max_length_generation": 512,
+    "precision": "fp32",
+    "load_in_8bit": false,
+    "load_in_4bit": false,
+    "left_padding": false,
+    "limit": null,
+    "limit_start": 0,
+    "save_every_k_tasks": -1,
+    "postprocess": true,
+    "allow_code_execution": true,
+    "generation_only": false,
+    "load_generations_path": "/gemini/platform/public/trained_models/sft/Qwen2_0.5B-2024.07.02-label.lingzhichat+finance+account+law-exp.00/checkpoint-1750/Results/Code/generations_mbpp.json",
+    "load_data_path": null,
+    "metric_output_path": "/gemini/platform/public/trained_models/sft/Qwen2_0.5B-2024.07.02-label.lingzhichat+finance+account+law-exp.00/checkpoint-1750/Results/Code/MBPP/evaluation_results.json",
+    "save_generations": false,
+    "load_generations_intermediate_paths": null,
+    "save_generations_path": "generations.json",
+    "save_references": false,
+    "save_references_path": "references.json",
+    "prompt": "prompt",
+    "max_memory_per_gpu": null,
+    "check_references": false
+  }
+}

Results/GSM8K/results.json

@@ -0,0 +1,112 @@
+{
+  "results": {
+    "gsm8k": {
+      "exact_match,strict-match": 0.2934040940106141,
+      "exact_match_stderr,strict-match": 0.012541830815461487,
+      "exact_match,flexible-extract": 0.2941622441243366,
+      "exact_match_stderr,flexible-extract": 0.012551285331470152,
+      "alias": "gsm8k"
+    }
+  },
+  "group_subtasks": {
+    "gsm8k": []
+  },
+  "configs": {
+    "gsm8k": {
+      "task": "gsm8k",
+      "group": [
+        "math_word_problems"
+      ],
+      "dataset_path": "gsm8k",
+      "dataset_name": "main",
+      "training_split": "train",
+      "test_split": "test",
+      "fewshot_split": "train",
+      "doc_to_text": "Question: {{question}}\nAnswer:",
+      "doc_to_target": "{{answer}}",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "exact_match",
+          "aggregation": "mean",
+          "higher_is_better": true,
+          "ignore_case": true,
+          "ignore_punctuation": false,
+          "regexes_to_ignore": [
+            ",",
+            "\\$",
+            "(?s).*#### ",
+            "\\.$"
+          ]
+        }
+      ],
+      "output_type": "generate_until",
+      "generation_kwargs": {
+        "until": [
+          "Question:",
+          "</s>",
+          "<|im_end|>"
+        ],
+        "do_sample": false,
+        "temperature": 0.0
+      },
+      "repeats": 1,
+      "filter_list": [
+        {
+          "name": "strict-match",
+          "filter": [
+            {
+              "function": "regex",
+              "regex_pattern": "#### (\\-?[0-9\\.\\,]+)"
+            },
+            {
+              "function": "take_first"
+            }
+          ]
+        },
+        {
+          "name": "flexible-extract",
+          "filter": [
+            {
+              "function": "regex",
+              "group_select": -1,
+              "regex_pattern": "(-?[$0-9.,]{2,})|(-?[0-9]+)"
+            },
+            {
+              "function": "take_first"
+            }
+          ]
+        }
+      ],
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 3.0
+      }
+    }
+  },
+  "versions": {
+    "gsm8k": 3.0
+  },
+  "n-shot": {
+    "gsm8k": 5
+  },
+  "config": {
+    "model": "hf",
+    "model_args": "pretrained=/gemini/platform/public/trained_models/sft/Qwen2_0.5B-2024.07.02-label.lingzhichat+finance+account+law-exp.00/checkpoint-1750",
+    "batch_size": "auto",
+    "batch_sizes": [],
+    "device": null,
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null
+  },
+  "git_hash": "3196e907",
+  "date": 1719996509.435399,
+  "pretty_env_info": "PyTorch version: 2.4.0a0+07cecf4168.nv24.05\nIs debug build: False\nCUDA used to build PyTorch: 12.4\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.4 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.29.2\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-5.4.0-144-generic-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.4.131\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA H800\nGPU 1: NVIDIA H800\nGPU 2: NVIDIA H800\nGPU 3: NVIDIA H800\nGPU 4: NVIDIA H800\nGPU 5: NVIDIA H800\nGPU 6: NVIDIA H800\nGPU 7: NVIDIA H800\n\nNvidia driver version: 535.129.03\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.1.0\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture:                    x86_64\nCPU op-mode(s):                  32-bit, 64-bit\nAddress sizes:                   46 bits physical, 57 bits virtual\nByte Order:                      Little Endian\nCPU(s):                          128\nOn-line CPU(s) list:             0-127\nVendor ID:                       GenuineIntel\nModel name:                      Intel(R) Xeon(R) Platinum 8462Y+\nCPU family:                      6\nModel:                           143\nThread(s) per core:              2\nCore(s) per socket:              32\nSocket(s):                       2\nStepping:                        8\nFrequency boost:                 enabled\nCPU max MHz:                     2801.0000\nCPU min MHz:                     800.0000\nBogoMIPS:                        5600.00\nFlags:                           fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 invpcid_single cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local avx512_bf16 wbnoinvd dtherm ida arat pln pts avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq rdpid cldemote movdiri movdir64b md_clear pconfig flush_l1d arch_capabilities\nVirtualization:                  VT-x\nL1d cache:                       3 MiB (64 instances)\nL1i cache:                       2 MiB (64 instances)\nL2 cache:                        128 MiB (64 instances)\nL3 cache:                        120 MiB (2 instances)\nNUMA node(s):                    2\nNUMA node0 CPU(s):               0-31,64-95\nNUMA node1 CPU(s):               32-63,96-127\nVulnerability Itlb multihit:     Not affected\nVulnerability L1tf:              Not affected\nVulnerability Mds:               Not affected\nVulnerability Meltdown:          Not affected\nVulnerability Mmio stale data:   Not affected\nVulnerability Retbleed:          Not affected\nVulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp\nVulnerability Spectre v1:        Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2:        Mitigation; Enhanced IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence\nVulnerability Srbds:             Not affected\nVulnerability Tsx async abort:   Not affected\n\nVersions of relevant libraries:\n[pip3] numpy==1.24.4\n[pip3] onnx==1.16.0\n[pip3] optree==0.11.0\n[pip3] pytorch-quantization==2.1.2\n[pip3] pytorch-triton==3.0.0+989adb9a2\n[pip3] torch==2.4.0a0+07cecf4168.nv24.5\n[pip3] torch-tensorrt==2.4.0a0\n[pip3] torchvision==0.19.0a0\n[conda] Could not collect",
+  "transformers_version": "4.41.2",
+  "upper_git_hash": null
+}

Results/MATHQA/results.json

@@ -0,0 +1,76 @@
+{
+  "results": {
+    "mathqa": {
+      "acc,none": 0.2917922948073702,
+      "acc_stderr,none": 0.00832181053996124,
+      "acc_norm,none": 0.2931323283082077,
+      "acc_norm_stderr,none": 0.00833300244579757,
+      "alias": "mathqa"
+    }
+  },
+  "group_subtasks": {
+    "mathqa": []
+  },
+  "configs": {
+    "mathqa": {
+      "task": "mathqa",
+      "group": [
+        "math_word_problems"
+      ],
+      "dataset_path": "math_qa",
+      "training_split": "train",
+      "validation_split": "validation",
+      "test_split": "test",
+      "doc_to_text": "Question: {{Problem}}\nAnswer:",
+      "doc_to_target": "{{['a', 'b', 'c', 'd', 'e'].index(correct)}}",
+      "doc_to_choice": "def doc_to_choice(doc):\n    choices = [\n        c[4:].rstrip(\" ,\")\n        for c in re.findall(r\"[abcd] \\) .*?, |e \\) .*?$\", doc[\"options\"])\n    ]\n    return choices\n",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": true,
+      "doc_to_decontamination_query": "Question: {{Problem}}\nAnswer:",
+      "metadata": {
+        "version": 1.0
+      }
+    }
+  },
+  "versions": {
+    "mathqa": 1.0
+  },
+  "n-shot": {
+    "mathqa": 0
+  },
+  "config": {
+    "model": "hf",
+    "model_args": "pretrained=/gemini/platform/public/trained_models/sft/Qwen2_0.5B-2024.07.02-label.lingzhichat+finance+account+law-exp.00/checkpoint-1750",
+    "batch_size": "auto",
+    "batch_sizes": [
+      64
+    ],
+    "device": null,
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null
+  },
+  "git_hash": "3196e907",
+  "date": 1719991136.7374132,
+  "pretty_env_info": "PyTorch version: 2.4.0a0+07cecf4168.nv24.05\nIs debug build: False\nCUDA used to build PyTorch: 12.4\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.4 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.29.2\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-5.4.0-144-generic-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.4.131\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA H800\nGPU 1: NVIDIA H800\nGPU 2: NVIDIA H800\nGPU 3: NVIDIA H800\nGPU 4: NVIDIA H800\nGPU 5: NVIDIA H800\nGPU 6: NVIDIA H800\nGPU 7: NVIDIA H800\n\nNvidia driver version: 535.129.03\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.1.0\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture:                    x86_64\nCPU op-mode(s):                  32-bit, 64-bit\nAddress sizes:                   46 bits physical, 57 bits virtual\nByte Order:                      Little Endian\nCPU(s):                          128\nOn-line CPU(s) list:             0-127\nVendor ID:                       GenuineIntel\nModel name:                      Intel(R) Xeon(R) Platinum 8462Y+\nCPU family:                      6\nModel:                           143\nThread(s) per core:              2\nCore(s) per socket:              32\nSocket(s):                       2\nStepping:                        8\nFrequency boost:                 enabled\nCPU max MHz:                     2801.0000\nCPU min MHz:                     800.0000\nBogoMIPS:                        5600.00\nFlags:                           fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 invpcid_single cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local avx512_bf16 wbnoinvd dtherm ida arat pln pts avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq rdpid cldemote movdiri movdir64b md_clear pconfig flush_l1d arch_capabilities\nVirtualization:                  VT-x\nL1d cache:                       3 MiB (64 instances)\nL1i cache:                       2 MiB (64 instances)\nL2 cache:                        128 MiB (64 instances)\nL3 cache:                        120 MiB (2 instances)\nNUMA node(s):                    2\nNUMA node0 CPU(s):               0-31,64-95\nNUMA node1 CPU(s):               32-63,96-127\nVulnerability Itlb multihit:     Not affected\nVulnerability L1tf:              Not affected\nVulnerability Mds:               Not affected\nVulnerability Meltdown:          Not affected\nVulnerability Mmio stale data:   Not affected\nVulnerability Retbleed:          Not affected\nVulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp\nVulnerability Spectre v1:        Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2:        Mitigation; Enhanced IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence\nVulnerability Srbds:             Not affected\nVulnerability Tsx async abort:   Not affected\n\nVersions of relevant libraries:\n[pip3] numpy==1.24.4\n[pip3] onnx==1.16.0\n[pip3] optree==0.11.0\n[pip3] pytorch-quantization==2.1.2\n[pip3] pytorch-triton==3.0.0+989adb9a2\n[pip3] torch==2.4.0a0+07cecf4168.nv24.5\n[pip3] torch-tensorrt==2.4.0a0\n[pip3] torchvision==0.19.0a0\n[conda] Could not collect",
+  "transformers_version": "4.41.2",
+  "upper_git_hash": null
+}

Results/MMLU/results.json

@@ -0,0 +1,2723 @@
+{
+  "results": {
+    "mmlu": {
+      "acc,none": 0.44245833926791056,
+      "acc_stderr,none": 0.004097625263954979,
+      "alias": "mmlu"
+    },
+    "mmlu_humanities": {
+      "alias": " - humanities",
+      "acc,none": 0.40403825717322,
+      "acc_stderr,none": 0.006942627946513873
+    },
+    "mmlu_formal_logic": {
+      "alias": "  - formal_logic",
+      "acc,none": 0.31746031746031744,
+      "acc_stderr,none": 0.041634530313028585
+    },
+    "mmlu_high_school_european_history": {
+      "alias": "  - high_school_european_history",
+      "acc,none": 0.5393939393939394,
+      "acc_stderr,none": 0.03892207016552013
+    },
+    "mmlu_high_school_us_history": {
+      "alias": "  - high_school_us_history",
+      "acc,none": 0.5343137254901961,
+      "acc_stderr,none": 0.03501038327635897
+    },
+    "mmlu_high_school_world_history": {
+      "alias": "  - high_school_world_history",
+      "acc,none": 0.6033755274261603,
+      "acc_stderr,none": 0.03184399873811225
+    },
+    "mmlu_international_law": {
+      "alias": "  - international_law",
+      "acc,none": 0.6776859504132231,
+      "acc_stderr,none": 0.042664163633521685
+    },
+    "mmlu_jurisprudence": {
+      "alias": "  - jurisprudence",
+      "acc,none": 0.6018518518518519,
+      "acc_stderr,none": 0.04732332615978813
+    },
+    "mmlu_logical_fallacies": {
+      "alias": "  - logical_fallacies",
+      "acc,none": 0.4539877300613497,
+      "acc_stderr,none": 0.0391170190467718
+    },
+    "mmlu_moral_disputes": {
+      "alias": "  - moral_disputes",
+      "acc,none": 0.5144508670520231,
+      "acc_stderr,none": 0.026907849856282542
+    },
+    "mmlu_moral_scenarios": {
+      "alias": "  - moral_scenarios",
+      "acc,none": 0.2424581005586592,
+      "acc_stderr,none": 0.014333522059217892
+    },
+    "mmlu_philosophy": {
+      "alias": "  - philosophy",
+      "acc,none": 0.48231511254019294,
+      "acc_stderr,none": 0.02838032284907713
+    },
+    "mmlu_prehistory": {
+      "alias": "  - prehistory",
+      "acc,none": 0.4537037037037037,
+      "acc_stderr,none": 0.0277012284685426
+    },
+    "mmlu_professional_law": {
+      "alias": "  - professional_law",
+      "acc,none": 0.3396349413298566,
+      "acc_stderr,none": 0.012095592506931974
+    },
+    "mmlu_world_religions": {
+      "alias": "  - world_religions",
+      "acc,none": 0.5029239766081871,
+      "acc_stderr,none": 0.03834759370936839
+    },
+    "mmlu_other": {
+      "alias": " - other",
+      "acc,none": 0.4766655938204055,
+      "acc_stderr,none": 0.008846010190081952
+    },
+    "mmlu_business_ethics": {
+      "alias": "  - business_ethics",
+      "acc,none": 0.47,
+      "acc_stderr,none": 0.050161355804659205
+    },
+    "mmlu_clinical_knowledge": {
+      "alias": "  - clinical_knowledge",
+      "acc,none": 0.4679245283018868,
+      "acc_stderr,none": 0.03070948699255654
+    },
+    "mmlu_college_medicine": {
+      "alias": "  - college_medicine",
+      "acc,none": 0.45664739884393063,
+      "acc_stderr,none": 0.03798106566014499
+    },
+    "mmlu_global_facts": {
+      "alias": "  - global_facts",
+      "acc,none": 0.32,
+      "acc_stderr,none": 0.04688261722621504
+    },
+    "mmlu_human_aging": {
+      "alias": "  - human_aging",
+      "acc,none": 0.4977578475336323,
+      "acc_stderr,none": 0.03355746535223264
+    },
+    "mmlu_management": {
+      "alias": "  - management",
+      "acc,none": 0.5825242718446602,
+      "acc_stderr,none": 0.048828405482122375
+    },
+    "mmlu_marketing": {
+      "alias": "  - marketing",
+      "acc,none": 0.6623931623931624,
+      "acc_stderr,none": 0.030980296992618558
+    },
+    "mmlu_medical_genetics": {
+      "alias": "  - medical_genetics",
+      "acc,none": 0.45,
+      "acc_stderr,none": 0.049999999999999996
+    },
+    "mmlu_miscellaneous": {
+      "alias": "  - miscellaneous",
+      "acc,none": 0.49808429118773945,
+      "acc_stderr,none": 0.017879832259026677
+    },
+    "mmlu_nutrition": {
+      "alias": "  - nutrition",
+      "acc,none": 0.5555555555555556,
+      "acc_stderr,none": 0.02845263998508801
+    },
+    "mmlu_professional_accounting": {
+      "alias": "  - professional_accounting",
+      "acc,none": 0.40070921985815605,
+      "acc_stderr,none": 0.029233465745573086
+    },
+    "mmlu_professional_medicine": {
+      "alias": "  - professional_medicine",
+      "acc,none": 0.33088235294117646,
+      "acc_stderr,none": 0.02858270975389843
+    },
+    "mmlu_virology": {
+      "alias": "  - virology",
+      "acc,none": 0.39156626506024095,
+      "acc_stderr,none": 0.03799857454479636
+    },
+    "mmlu_social_sciences": {
+      "alias": " - social_sciences",
+      "acc,none": 0.5138121546961326,
+      "acc_stderr,none": 0.008898530360448643
+    },
+    "mmlu_econometrics": {
+      "alias": "  - econometrics",
+      "acc,none": 0.32456140350877194,
+      "acc_stderr,none": 0.04404556157374768
+    },
+    "mmlu_high_school_geography": {
+      "alias": "  - high_school_geography",
+      "acc,none": 0.5252525252525253,
+      "acc_stderr,none": 0.035578062450873145
+    },
+    "mmlu_high_school_government_and_politics": {
+      "alias": "  - high_school_government_and_politics",
+      "acc,none": 0.5647668393782384,
+      "acc_stderr,none": 0.03578038165008586
+    },
+    "mmlu_high_school_macroeconomics": {
+      "alias": "  - high_school_macroeconomics",
+      "acc,none": 0.4282051282051282,
+      "acc_stderr,none": 0.02508830145469483
+    },
+    "mmlu_high_school_microeconomics": {
+      "alias": "  - high_school_microeconomics",
+      "acc,none": 0.4831932773109244,
+      "acc_stderr,none": 0.03246013680375308
+    },
+    "mmlu_high_school_psychology": {
+      "alias": "  - high_school_psychology",
+      "acc,none": 0.5944954128440367,
+      "acc_stderr,none": 0.02105099799189684
+    },
+    "mmlu_human_sexuality": {
+      "alias": "  - human_sexuality",
+      "acc,none": 0.549618320610687,
+      "acc_stderr,none": 0.04363643698524779
+    },
+    "mmlu_professional_psychology": {
+      "alias": "  - professional_psychology",
+      "acc,none": 0.4297385620915033,
+      "acc_stderr,none": 0.020027122784928554
+    },
+    "mmlu_public_relations": {
+      "alias": "  - public_relations",
+      "acc,none": 0.5363636363636364,
+      "acc_stderr,none": 0.047764491623961985
+    },
+    "mmlu_security_studies": {
+      "alias": "  - security_studies",
+      "acc,none": 0.5551020408163265,
+      "acc_stderr,none": 0.031814251181977865
+    },
+    "mmlu_sociology": {
+      "alias": "  - sociology",
+      "acc,none": 0.6268656716417911,
+      "acc_stderr,none": 0.03419832608176007
+    },
+    "mmlu_us_foreign_policy": {
+      "alias": "  - us_foreign_policy",
+      "acc,none": 0.69,
+      "acc_stderr,none": 0.04648231987117316
+    },
+    "mmlu_stem": {
+      "alias": " - stem",
+      "acc,none": 0.3964478274659055,
+      "acc_stderr,none": 0.0086195325195511
+    },
+    "mmlu_abstract_algebra": {
+      "alias": "  - abstract_algebra",
+      "acc,none": 0.35,
+      "acc_stderr,none": 0.047937248544110196
+    },
+    "mmlu_anatomy": {
+      "alias": "  - anatomy",
+      "acc,none": 0.45925925925925926,
+      "acc_stderr,none": 0.04304979692464242
+    },
+    "mmlu_astronomy": {
+      "alias": "  - astronomy",
+      "acc,none": 0.46710526315789475,
+      "acc_stderr,none": 0.04060127035236397
+    },
+    "mmlu_college_biology": {
+      "alias": "  - college_biology",
+      "acc,none": 0.3680555555555556,
+      "acc_stderr,none": 0.040329990539607195
+    },
+    "mmlu_college_chemistry": {
+      "alias": "  - college_chemistry",
+      "acc,none": 0.29,
+      "acc_stderr,none": 0.045604802157206845
+    },
+    "mmlu_college_computer_science": {
+      "alias": "  - college_computer_science",
+      "acc,none": 0.37,
+      "acc_stderr,none": 0.048523658709391
+    },
+    "mmlu_college_mathematics": {
+      "alias": "  - college_mathematics",
+      "acc,none": 0.26,
+      "acc_stderr,none": 0.044084400227680794
+    },
+    "mmlu_college_physics": {
+      "alias": "  - college_physics",
+      "acc,none": 0.2549019607843137,
+      "acc_stderr,none": 0.04336432707993176
+    },
+    "mmlu_computer_security": {
+      "alias": "  - computer_security",
+      "acc,none": 0.51,
+      "acc_stderr,none": 0.05024183937956913
+    },
+    "mmlu_conceptual_physics": {
+      "alias": "  - conceptual_physics",
+      "acc,none": 0.3829787234042553,
+      "acc_stderr,none": 0.03177821250236922
+    },
+    "mmlu_electrical_engineering": {
+      "alias": "  - electrical_engineering",
+      "acc,none": 0.5310344827586206,
+      "acc_stderr,none": 0.04158632762097828
+    },
+    "mmlu_elementary_mathematics": {
+      "alias": "  - elementary_mathematics",
+      "acc,none": 0.4021164021164021,
+      "acc_stderr,none": 0.025253032554997695
+    },
+    "mmlu_high_school_biology": {
+      "alias": "  - high_school_biology",
+      "acc,none": 0.47419354838709676,
+      "acc_stderr,none": 0.02840609505765332
+    },
+    "mmlu_high_school_chemistry": {
+      "alias": "  - high_school_chemistry",
+      "acc,none": 0.43842364532019706,
+      "acc_stderr,none": 0.03491207857486519
+    },
+    "mmlu_high_school_computer_science": {
+      "alias": "  - high_school_computer_science",
+      "acc,none": 0.58,
+      "acc_stderr,none": 0.049604496374885836
+    },
+    "mmlu_high_school_mathematics": {
+      "alias": "  - high_school_mathematics",
+      "acc,none": 0.34444444444444444,
+      "acc_stderr,none": 0.028972648884844267
+    },
+    "mmlu_high_school_physics": {
+      "alias": "  - high_school_physics",
+      "acc,none": 0.2781456953642384,
+      "acc_stderr,none": 0.03658603262763743
+    },
+    "mmlu_high_school_statistics": {
+      "alias": "  - high_school_statistics",
+      "acc,none": 0.35648148148148145,
+      "acc_stderr,none": 0.03266478331527272
+    },
+    "mmlu_machine_learning": {
+      "alias": "  - machine_learning",
+      "acc,none": 0.3125,
+      "acc_stderr,none": 0.043994650575715215
+    }
+  },
+  "groups": {
+    "mmlu": {
+      "acc,none": 0.44245833926791056,
+      "acc_stderr,none": 0.004097625263954979,
+      "alias": "mmlu"
+    },
+    "mmlu_humanities": {
+      "alias": " - humanities",
+      "acc,none": 0.40403825717322,
+      "acc_stderr,none": 0.006942627946513873
+    },
+    "mmlu_other": {
+      "alias": " - other",
+      "acc,none": 0.4766655938204055,
+      "acc_stderr,none": 0.008846010190081952
+    },
+    "mmlu_social_sciences": {
+      "alias": " - social_sciences",
+      "acc,none": 0.5138121546961326,
+      "acc_stderr,none": 0.008898530360448643
+    },
+    "mmlu_stem": {
+      "alias": " - stem",
+      "acc,none": 0.3964478274659055,
+      "acc_stderr,none": 0.0086195325195511
+    }
+  },
+  "group_subtasks": {
+    "mmlu_stem": [
+      "mmlu_high_school_mathematics",
+      "mmlu_high_school_computer_science",
+      "mmlu_high_school_chemistry",
+      "mmlu_electrical_engineering",
+      "mmlu_college_mathematics",
+      "mmlu_college_chemistry",
+      "mmlu_college_biology",
+      "mmlu_astronomy",
+      "mmlu_high_school_physics",
+      "mmlu_computer_security",
+      "mmlu_college_computer_science",
+      "mmlu_anatomy",
+      "mmlu_abstract_algebra",
+      "mmlu_high_school_biology",
+      "mmlu_machine_learning",
+      "mmlu_high_school_statistics",
+      "mmlu_elementary_mathematics",
+      "mmlu_conceptual_physics",
+      "mmlu_college_physics"
+    ],
+    "mmlu_other": [
+      "mmlu_marketing",
+      "mmlu_management",
+      "mmlu_human_aging",
+      "mmlu_global_facts",
+      "mmlu_business_ethics",
+      "mmlu_miscellaneous",
+      "mmlu_clinical_knowledge",
+      "mmlu_professional_accounting",
+      "mmlu_nutrition",
+      "mmlu_college_medicine",
+      "mmlu_virology",
+      "mmlu_professional_medicine",
+      "mmlu_medical_genetics"
+    ],
+    "mmlu_social_sciences": [
+      "mmlu_sociology",
+      "mmlu_econometrics",
+      "mmlu_us_foreign_policy",
+      "mmlu_security_studies",
+      "mmlu_high_school_macroeconomics",
+      "mmlu_public_relations",
+      "mmlu_professional_psychology",
+      "mmlu_human_sexuality",
+      "mmlu_high_school_psychology",
+      "mmlu_high_school_microeconomics",
+      "mmlu_high_school_government_and_politics",
+      "mmlu_high_school_geography"
+    ],
+    "mmlu_humanities": [
+      "mmlu_professional_law",
+      "mmlu_prehistory",
+      "mmlu_philosophy",
+      "mmlu_formal_logic",
+      "mmlu_moral_scenarios",
+      "mmlu_high_school_world_history",
+      "mmlu_high_school_european_history",
+      "mmlu_world_religions",
+      "mmlu_moral_disputes",
+      "mmlu_international_law",
+      "mmlu_high_school_us_history",
+      "mmlu_jurisprudence",
+      "mmlu_logical_fallacies"
+    ],
+    "mmlu": [
+      "mmlu_humanities",
+      "mmlu_social_sciences",
+      "mmlu_other",
+      "mmlu_stem"
+    ]
+  },
+  "configs": {
+    "mmlu_abstract_algebra": {
+      "task": "mmlu_abstract_algebra",
+      "task_alias": "abstract_algebra",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "abstract_algebra",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about abstract algebra.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_anatomy": {
+      "task": "mmlu_anatomy",
+      "task_alias": "anatomy",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "anatomy",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about anatomy.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_astronomy": {
+      "task": "mmlu_astronomy",
+      "task_alias": "astronomy",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "astronomy",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about astronomy.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_business_ethics": {
+      "task": "mmlu_business_ethics",
+      "task_alias": "business_ethics",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "business_ethics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about business ethics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_clinical_knowledge": {
+      "task": "mmlu_clinical_knowledge",
+      "task_alias": "clinical_knowledge",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "clinical_knowledge",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about clinical knowledge.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_college_biology": {
+      "task": "mmlu_college_biology",
+      "task_alias": "college_biology",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "college_biology",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about college biology.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_college_chemistry": {
+      "task": "mmlu_college_chemistry",
+      "task_alias": "college_chemistry",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "college_chemistry",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about college chemistry.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_college_computer_science": {
+      "task": "mmlu_college_computer_science",
+      "task_alias": "college_computer_science",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "college_computer_science",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about college computer science.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_college_mathematics": {
+      "task": "mmlu_college_mathematics",
+      "task_alias": "college_mathematics",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "college_mathematics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about college mathematics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_college_medicine": {
+      "task": "mmlu_college_medicine",
+      "task_alias": "college_medicine",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "college_medicine",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about college medicine.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_college_physics": {
+      "task": "mmlu_college_physics",
+      "task_alias": "college_physics",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "college_physics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about college physics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_computer_security": {
+      "task": "mmlu_computer_security",
+      "task_alias": "computer_security",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "computer_security",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about computer security.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_conceptual_physics": {
+      "task": "mmlu_conceptual_physics",
+      "task_alias": "conceptual_physics",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "conceptual_physics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about conceptual physics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_econometrics": {
+      "task": "mmlu_econometrics",
+      "task_alias": "econometrics",
+      "group": "mmlu_social_sciences",
+      "group_alias": "social_sciences",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "econometrics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about econometrics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_electrical_engineering": {
+      "task": "mmlu_electrical_engineering",
+      "task_alias": "electrical_engineering",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "electrical_engineering",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about electrical engineering.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_elementary_mathematics": {
+      "task": "mmlu_elementary_mathematics",
+      "task_alias": "elementary_mathematics",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "elementary_mathematics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about elementary mathematics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_formal_logic": {
+      "task": "mmlu_formal_logic",
+      "task_alias": "formal_logic",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "formal_logic",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about formal logic.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_global_facts": {
+      "task": "mmlu_global_facts",
+      "task_alias": "global_facts",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "global_facts",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about global facts.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_biology": {
+      "task": "mmlu_high_school_biology",
+      "task_alias": "high_school_biology",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_biology",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school biology.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_chemistry": {
+      "task": "mmlu_high_school_chemistry",
+      "task_alias": "high_school_chemistry",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_chemistry",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school chemistry.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_computer_science": {
+      "task": "mmlu_high_school_computer_science",
+      "task_alias": "high_school_computer_science",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_computer_science",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school computer science.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_european_history": {
+      "task": "mmlu_high_school_european_history",
+      "task_alias": "high_school_european_history",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_european_history",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school european history.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_geography": {
+      "task": "mmlu_high_school_geography",
+      "task_alias": "high_school_geography",
+      "group": "mmlu_social_sciences",
+      "group_alias": "social_sciences",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_geography",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school geography.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_government_and_politics": {
+      "task": "mmlu_high_school_government_and_politics",
+      "task_alias": "high_school_government_and_politics",
+      "group": "mmlu_social_sciences",
+      "group_alias": "social_sciences",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_government_and_politics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school government and politics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_macroeconomics": {
+      "task": "mmlu_high_school_macroeconomics",
+      "task_alias": "high_school_macroeconomics",
+      "group": "mmlu_social_sciences",
+      "group_alias": "social_sciences",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_macroeconomics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school macroeconomics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_mathematics": {
+      "task": "mmlu_high_school_mathematics",
+      "task_alias": "high_school_mathematics",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_mathematics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school mathematics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_microeconomics": {
+      "task": "mmlu_high_school_microeconomics",
+      "task_alias": "high_school_microeconomics",
+      "group": "mmlu_social_sciences",
+      "group_alias": "social_sciences",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_microeconomics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school microeconomics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_physics": {
+      "task": "mmlu_high_school_physics",
+      "task_alias": "high_school_physics",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_physics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school physics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_psychology": {
+      "task": "mmlu_high_school_psychology",
+      "task_alias": "high_school_psychology",
+      "group": "mmlu_social_sciences",
+      "group_alias": "social_sciences",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_psychology",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school psychology.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_statistics": {
+      "task": "mmlu_high_school_statistics",
+      "task_alias": "high_school_statistics",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_statistics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school statistics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_us_history": {
+      "task": "mmlu_high_school_us_history",
+      "task_alias": "high_school_us_history",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_us_history",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school us history.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_world_history": {
+      "task": "mmlu_high_school_world_history",
+      "task_alias": "high_school_world_history",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_world_history",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school world history.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_human_aging": {
+      "task": "mmlu_human_aging",
+      "task_alias": "human_aging",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "human_aging",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about human aging.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_human_sexuality": {
+      "task": "mmlu_human_sexuality",
+      "task_alias": "human_sexuality",
+      "group": "mmlu_social_sciences",
+      "group_alias": "social_sciences",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "human_sexuality",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about human sexuality.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_international_law": {
+      "task": "mmlu_international_law",
+      "task_alias": "international_law",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "international_law",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about international law.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_jurisprudence": {
+      "task": "mmlu_jurisprudence",
+      "task_alias": "jurisprudence",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "jurisprudence",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about jurisprudence.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_logical_fallacies": {
+      "task": "mmlu_logical_fallacies",
+      "task_alias": "logical_fallacies",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "logical_fallacies",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about logical fallacies.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_machine_learning": {
+      "task": "mmlu_machine_learning",
+      "task_alias": "machine_learning",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "machine_learning",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about machine learning.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_management": {
+      "task": "mmlu_management",
+      "task_alias": "management",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "management",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about management.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_marketing": {
+      "task": "mmlu_marketing",
+      "task_alias": "marketing",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "marketing",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about marketing.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_medical_genetics": {
+      "task": "mmlu_medical_genetics",
+      "task_alias": "medical_genetics",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "medical_genetics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about medical genetics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_miscellaneous": {
+      "task": "mmlu_miscellaneous",
+      "task_alias": "miscellaneous",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "miscellaneous",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about miscellaneous.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_moral_disputes": {
+      "task": "mmlu_moral_disputes",
+      "task_alias": "moral_disputes",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "moral_disputes",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about moral disputes.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_moral_scenarios": {
+      "task": "mmlu_moral_scenarios",
+      "task_alias": "moral_scenarios",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "moral_scenarios",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about moral scenarios.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_nutrition": {
+      "task": "mmlu_nutrition",
+      "task_alias": "nutrition",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "nutrition",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about nutrition.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_philosophy": {
+      "task": "mmlu_philosophy",
+      "task_alias": "philosophy",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "philosophy",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about philosophy.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_prehistory": {
+      "task": "mmlu_prehistory",
+      "task_alias": "prehistory",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "prehistory",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about prehistory.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_professional_accounting": {
+      "task": "mmlu_professional_accounting",
+      "task_alias": "professional_accounting",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "professional_accounting",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about professional accounting.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_professional_law": {
+      "task": "mmlu_professional_law",
+      "task_alias": "professional_law",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "professional_law",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about professional law.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_professional_medicine": {
+      "task": "mmlu_professional_medicine",
+      "task_alias": "professional_medicine",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "professional_medicine",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about professional medicine.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_professional_psychology": {
+      "task": "mmlu_professional_psychology",
+      "task_alias": "professional_psychology",
+      "group": "mmlu_social_sciences",
+      "group_alias": "social_sciences",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "professional_psychology",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about professional psychology.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_public_relations": {
+      "task": "mmlu_public_relations",
+      "task_alias": "public_relations",
+      "group": "mmlu_social_sciences",
+      "group_alias": "social_sciences",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "public_relations",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about public relations.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_security_studies": {
+      "task": "mmlu_security_studies",
+      "task_alias": "security_studies",
+      "group": "mmlu_social_sciences",
+      "group_alias": "social_sciences",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "security_studies",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about security studies.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_sociology": {
+      "task": "mmlu_sociology",
+      "task_alias": "sociology",
+      "group": "mmlu_social_sciences",
+      "group_alias": "social_sciences",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "sociology",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about sociology.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_us_foreign_policy": {
+      "task": "mmlu_us_foreign_policy",
+      "task_alias": "us_foreign_policy",
+      "group": "mmlu_social_sciences",
+      "group_alias": "social_sciences",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "us_foreign_policy",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about us foreign policy.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_virology": {
+      "task": "mmlu_virology",
+      "task_alias": "virology",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "virology",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about virology.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_world_religions": {
+      "task": "mmlu_world_religions",
+      "task_alias": "world_religions",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "world_religions",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about world religions.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    }
+  },
+  "versions": {
+    "mmlu_abstract_algebra": 0.0,
+    "mmlu_anatomy": 0.0,
+    "mmlu_astronomy": 0.0,
+    "mmlu_business_ethics": 0.0,
+    "mmlu_clinical_knowledge": 0.0,
+    "mmlu_college_biology": 0.0,
+    "mmlu_college_chemistry": 0.0,
+    "mmlu_college_computer_science": 0.0,
+    "mmlu_college_mathematics": 0.0,
+    "mmlu_college_medicine": 0.0,
+    "mmlu_college_physics": 0.0,
+    "mmlu_computer_security": 0.0,
+    "mmlu_conceptual_physics": 0.0,
+    "mmlu_econometrics": 0.0,
+    "mmlu_electrical_engineering": 0.0,
+    "mmlu_elementary_mathematics": 0.0,
+    "mmlu_formal_logic": 0.0,
+    "mmlu_global_facts": 0.0,
+    "mmlu_high_school_biology": 0.0,
+    "mmlu_high_school_chemistry": 0.0,
+    "mmlu_high_school_computer_science": 0.0,
+    "mmlu_high_school_european_history": 0.0,
+    "mmlu_high_school_geography": 0.0,
+    "mmlu_high_school_government_and_politics": 0.0,
+    "mmlu_high_school_macroeconomics": 0.0,
+    "mmlu_high_school_mathematics": 0.0,
+    "mmlu_high_school_microeconomics": 0.0,
+    "mmlu_high_school_physics": 0.0,
+    "mmlu_high_school_psychology": 0.0,
+    "mmlu_high_school_statistics": 0.0,
+    "mmlu_high_school_us_history": 0.0,
+    "mmlu_high_school_world_history": 0.0,
+    "mmlu_human_aging": 0.0,
+    "mmlu_human_sexuality": 0.0,
+    "mmlu_international_law": 0.0,
+    "mmlu_jurisprudence": 0.0,
+    "mmlu_logical_fallacies": 0.0,
+    "mmlu_machine_learning": 0.0,
+    "mmlu_management": 0.0,
+    "mmlu_marketing": 0.0,
+    "mmlu_medical_genetics": 0.0,
+    "mmlu_miscellaneous": 0.0,
+    "mmlu_moral_disputes": 0.0,
+    "mmlu_moral_scenarios": 0.0,
+    "mmlu_nutrition": 0.0,
+    "mmlu_philosophy": 0.0,
+    "mmlu_prehistory": 0.0,
+    "mmlu_professional_accounting": 0.0,
+    "mmlu_professional_law": 0.0,
+    "mmlu_professional_medicine": 0.0,
+    "mmlu_professional_psychology": 0.0,
+    "mmlu_public_relations": 0.0,
+    "mmlu_security_studies": 0.0,
+    "mmlu_sociology": 0.0,
+    "mmlu_us_foreign_policy": 0.0,
+    "mmlu_virology": 0.0,
+    "mmlu_world_religions": 0.0
+  },
+  "n-shot": {
+    "mmlu": 0,
+    "mmlu_abstract_algebra": 0,
+    "mmlu_anatomy": 0,
+    "mmlu_astronomy": 0,
+    "mmlu_business_ethics": 0,
+    "mmlu_clinical_knowledge": 0,
+    "mmlu_college_biology": 0,
+    "mmlu_college_chemistry": 0,
+    "mmlu_college_computer_science": 0,
+    "mmlu_college_mathematics": 0,
+    "mmlu_college_medicine": 0,
+    "mmlu_college_physics": 0,
+    "mmlu_computer_security": 0,
+    "mmlu_conceptual_physics": 0,
+    "mmlu_econometrics": 0,
+    "mmlu_electrical_engineering": 0,
+    "mmlu_elementary_mathematics": 0,
+    "mmlu_formal_logic": 0,
+    "mmlu_global_facts": 0,
+    "mmlu_high_school_biology": 0,
+    "mmlu_high_school_chemistry": 0,
+    "mmlu_high_school_computer_science": 0,
+    "mmlu_high_school_european_history": 0,
+    "mmlu_high_school_geography": 0,
+    "mmlu_high_school_government_and_politics": 0,
+    "mmlu_high_school_macroeconomics": 0,
+    "mmlu_high_school_mathematics": 0,
+    "mmlu_high_school_microeconomics": 0,
+    "mmlu_high_school_physics": 0,
+    "mmlu_high_school_psychology": 0,
+    "mmlu_high_school_statistics": 0,
+    "mmlu_high_school_us_history": 0,
+    "mmlu_high_school_world_history": 0,
+    "mmlu_human_aging": 0,
+    "mmlu_human_sexuality": 0,
+    "mmlu_humanities": 0,
+    "mmlu_international_law": 0,
+    "mmlu_jurisprudence": 0,
+    "mmlu_logical_fallacies": 0,
+    "mmlu_machine_learning": 0,
+    "mmlu_management": 0,
+    "mmlu_marketing": 0,
+    "mmlu_medical_genetics": 0,
+    "mmlu_miscellaneous": 0,
+    "mmlu_moral_disputes": 0,
+    "mmlu_moral_scenarios": 0,
+    "mmlu_nutrition": 0,
+    "mmlu_other": 0,
+    "mmlu_philosophy": 0,
+    "mmlu_prehistory": 0,
+    "mmlu_professional_accounting": 0,
+    "mmlu_professional_law": 0,
+    "mmlu_professional_medicine": 0,
+    "mmlu_professional_psychology": 0,
+    "mmlu_public_relations": 0,
+    "mmlu_security_studies": 0,
+    "mmlu_social_sciences": 0,
+    "mmlu_sociology": 0,
+    "mmlu_stem": 0,
+    "mmlu_us_foreign_policy": 0,
+    "mmlu_virology": 0,
+    "mmlu_world_religions": 0
+  },
+  "config": {
+    "model": "hf",
+    "model_args": "pretrained=/gemini/platform/public/trained_models/sft/Qwen2_0.5B-2024.07.02-label.lingzhichat+finance+account+law-exp.00/checkpoint-1750",
+    "batch_size": "auto",
+    "batch_sizes": [
+      32
+    ],
+    "device": null,
+    "use_cache": null,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "gen_kwargs": null
+  },
+  "git_hash": "3196e907",
+  "date": 1719990878.587922,
+  "pretty_env_info": "PyTorch version: 2.4.0a0+07cecf4168.nv24.05\nIs debug build: False\nCUDA used to build PyTorch: 12.4\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.4 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.29.2\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-5.4.0-144-generic-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.4.131\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA H800\nGPU 1: NVIDIA H800\nGPU 2: NVIDIA H800\nGPU 3: NVIDIA H800\nGPU 4: NVIDIA H800\nGPU 5: NVIDIA H800\nGPU 6: NVIDIA H800\nGPU 7: NVIDIA H800\n\nNvidia driver version: 535.129.03\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.1.0\n/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.1.0\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitecture:                    x86_64\nCPU op-mode(s):                  32-bit, 64-bit\nAddress sizes:                   46 bits physical, 57 bits virtual\nByte Order:                      Little Endian\nCPU(s):                          128\nOn-line CPU(s) list:             0-127\nVendor ID:                       GenuineIntel\nModel name:                      Intel(R) Xeon(R) Platinum 8462Y+\nCPU family:                      6\nModel:                           143\nThread(s) per core:              2\nCore(s) per socket:              32\nSocket(s):                       2\nStepping:                        8\nFrequency boost:                 enabled\nCPU max MHz:                     2801.0000\nCPU min MHz:                     800.0000\nBogoMIPS:                        5600.00\nFlags:                           fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 invpcid_single cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local avx512_bf16 wbnoinvd dtherm ida arat pln pts avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq rdpid cldemote movdiri movdir64b md_clear pconfig flush_l1d arch_capabilities\nVirtualization:                  VT-x\nL1d cache:                       3 MiB (64 instances)\nL1i cache:                       2 MiB (64 instances)\nL2 cache:                        128 MiB (64 instances)\nL3 cache:                        120 MiB (2 instances)\nNUMA node(s):                    2\nNUMA node0 CPU(s):               0-31,64-95\nNUMA node1 CPU(s):               32-63,96-127\nVulnerability Itlb multihit:     Not affected\nVulnerability L1tf:              Not affected\nVulnerability Mds:               Not affected\nVulnerability Meltdown:          Not affected\nVulnerability Mmio stale data:   Not affected\nVulnerability Retbleed:          Not affected\nVulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp\nVulnerability Spectre v1:        Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2:        Mitigation; Enhanced IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence\nVulnerability Srbds:             Not affected\nVulnerability Tsx async abort:   Not affected\n\nVersions of relevant libraries:\n[pip3] numpy==1.24.4\n[pip3] onnx==1.16.0\n[pip3] optree==0.11.0\n[pip3] pytorch-quantization==2.1.2\n[pip3] pytorch-triton==3.0.0+989adb9a2\n[pip3] torch==2.4.0a0+07cecf4168.nv24.5\n[pip3] torch-tensorrt==2.4.0a0\n[pip3] torchvision==0.19.0a0\n[conda] Could not collect",
+  "transformers_version": "4.41.2",
+  "upper_git_hash": null
+}

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/gemini/platform/public/llm/huggingface/Qwen/Qwen2-0.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.42.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.42.2"
+}

latest

@@ -0,0 +1 @@
+global_step1750

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7279f763f24ae41dd763759456de5b051519d36a75a191755aab0d571ea4fdff
+size 988097536

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08282b46825aa78d10fe10e3fea89555c5b5a691b261a3ddfd58fcb58370edff
+size 15984

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbab71d98a3a9a92df82a6bba463947327c3a1bcf35cd9f4f46114641fc42dd9
+size 15984

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caac82d57d878d30219a4f9ec289a97ff90c53afc160b968f251b3fd3454b8d8
+size 15984

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19762d2d370222b01817da11bbaa6665d542293373186d66f754e7246bb861ed
+size 15984

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00c7508b346a7d3c5c23392845f1d013331114ade778794b76e919cb3ed5d33e
+size 15984

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b89de7d14dd20a191f56b74c816ef8b7fe5c171e31efbeadbf321c4539ed68c3
+size 15984

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c71152053553e6e22d670fbc4fd7550bf8a046b54cad7b71869787986a6a42c
+size 15984

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b67db12a26a26ffe03d9afc84a43857eb2e5b2fec2dd189653b415f74208190
+size 15984

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbd46ab5db65c10396897f14810422d3298269ee23ffadb0063f5707da7f5dcc
+size 1064

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,278 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.1432945499081444,
+  "eval_steps": 500,
+  "global_step": 1750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0612369871402327,
+      "grad_norm": 0.8098917283898412,
+      "learning_rate": 9.996294850025658e-06,
+      "loss": 1.0009,
+      "step": 50
+    },
+    {
+      "epoch": 0.1224739742804654,
+      "grad_norm": 0.8351009158740302,
+      "learning_rate": 9.985184891357165e-06,
+      "loss": 0.9902,
+      "step": 100
+    },
+    {
+      "epoch": 0.1837109614206981,
+      "grad_norm": 0.7857771081781793,
+      "learning_rate": 9.96668658961975e-06,
+      "loss": 0.972,
+      "step": 150
+    },
+    {
+      "epoch": 0.2449479485609308,
+      "grad_norm": 0.7820326486942377,
+      "learning_rate": 9.940827360406297e-06,
+      "loss": 0.9727,
+      "step": 200
+    },
+    {
+      "epoch": 0.3061849357011635,
+      "grad_norm": 0.7529490157497454,
+      "learning_rate": 9.907645528645791e-06,
+      "loss": 0.9652,
+      "step": 250
+    },
+    {
+      "epoch": 0.3674219228413962,
+      "grad_norm": 0.8000880788190894,
+      "learning_rate": 9.867190271803466e-06,
+      "loss": 0.9661,
+      "step": 300
+    },
+    {
+      "epoch": 0.4286589099816289,
+      "grad_norm": 0.7925477606605517,
+      "learning_rate": 9.819521546996864e-06,
+      "loss": 0.9599,
+      "step": 350
+    },
+    {
+      "epoch": 0.4898958971218616,
+      "grad_norm": 0.7624902603510945,
+      "learning_rate": 9.764710002135784e-06,
+      "loss": 0.9547,
+      "step": 400
+    },
+    {
+      "epoch": 0.5511328842620943,
+      "grad_norm": 0.7431039272381413,
+      "learning_rate": 9.702836871217838e-06,
+      "loss": 0.9466,
+      "step": 450
+    },
+    {
+      "epoch": 0.612369871402327,
+      "grad_norm": 0.7574806145615771,
+      "learning_rate": 9.633993853934803e-06,
+      "loss": 0.9439,
+      "step": 500
+    },
+    {
+      "epoch": 0.6736068585425597,
+      "grad_norm": 0.748375839743952,
+      "learning_rate": 9.558282979768164e-06,
+      "loss": 0.9429,
+      "step": 550
+    },
+    {
+      "epoch": 0.7348438456827924,
+      "grad_norm": 0.7952459759871126,
+      "learning_rate": 9.475816456775313e-06,
+      "loss": 0.9366,
+      "step": 600
+    },
+    {
+      "epoch": 0.7960808328230251,
+      "grad_norm": 0.7782924796375454,
+      "learning_rate": 9.386716505290467e-06,
+      "loss": 0.9356,
+      "step": 650
+    },
+    {
+      "epoch": 0.8573178199632578,
+      "grad_norm": 0.7443095452962357,
+      "learning_rate": 9.291115176786814e-06,
+      "loss": 0.9304,
+      "step": 700
+    },
+    {
+      "epoch": 0.9185548071034905,
+      "grad_norm": 0.7822224402996899,
+      "learning_rate": 9.189154158168293e-06,
+      "loss": 0.9339,
+      "step": 750
+    },
+    {
+      "epoch": 0.9797917942437232,
+      "grad_norm": 0.7817236760492132,
+      "learning_rate": 9.08098456178111e-06,
+      "loss": 0.9295,
+      "step": 800
+    },
+    {
+      "epoch": 1.0410287813839558,
+      "grad_norm": 0.7824573951031337,
+      "learning_rate": 8.966766701456177e-06,
+      "loss": 0.9029,
+      "step": 850
+    },
+    {
+      "epoch": 1.1022657685241886,
+      "grad_norm": 0.7621342939491088,
+      "learning_rate": 8.846669854914395e-06,
+      "loss": 0.8871,
+      "step": 900
+    },
+    {
+      "epoch": 1.1635027556644213,
+      "grad_norm": 0.7431557953761879,
+      "learning_rate": 8.720872012886918e-06,
+      "loss": 0.882,
+      "step": 950
+    },
+    {
+      "epoch": 1.224739742804654,
+      "grad_norm": 0.3886245437993066,
+      "learning_rate": 8.58955961532221e-06,
+      "loss": 0.8864,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2859767299448868,
+      "grad_norm": 0.7536794211653792,
+      "learning_rate": 8.452927275070858e-06,
+      "loss": 0.8805,
+      "step": 1050
+    },
+    {
+      "epoch": 1.3472137170851193,
+      "grad_norm": 0.7577244481174435,
+      "learning_rate": 8.311177489457653e-06,
+      "loss": 0.8855,
+      "step": 1100
+    },
+    {
+      "epoch": 1.408450704225352,
+      "grad_norm": 0.777343889968524,
+      "learning_rate": 8.164520340168404e-06,
+      "loss": 0.8862,
+      "step": 1150
+    },
+    {
+      "epoch": 1.4696876913655847,
+      "grad_norm": 0.736623306272446,
+      "learning_rate": 8.013173181896283e-06,
+      "loss": 0.8839,
+      "step": 1200
+    },
+    {
+      "epoch": 1.5309246785058175,
+      "grad_norm": 0.7451843323741638,
+      "learning_rate": 7.857360320209126e-06,
+      "loss": 0.8738,
+      "step": 1250
+    },
+    {
+      "epoch": 1.5921616656460502,
+      "grad_norm": 0.8023889052201314,
+      "learning_rate": 7.700553608573257e-06,
+      "loss": 0.8846,
+      "step": 1300
+    },
+    {
+      "epoch": 1.653398652786283,
+      "grad_norm": 0.7595177276389167,
+      "learning_rate": 7.536585976390474e-06,
+      "loss": 0.8818,
+      "step": 1350
+    },
+    {
+      "epoch": 1.7146356399265157,
+      "grad_norm": 0.7673121148739883,
+      "learning_rate": 7.3688589716215555e-06,
+      "loss": 0.8775,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7758726270667484,
+      "grad_norm": 0.7577794985624852,
+      "learning_rate": 7.197621175749467e-06,
+      "loss": 0.8738,
+      "step": 1450
+    },
+    {
+      "epoch": 1.8371096142069812,
+      "grad_norm": 0.7927915981856463,
+      "learning_rate": 7.023126373460202e-06,
+      "loss": 0.8771,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8983466013472137,
+      "grad_norm": 0.7595080397715767,
+      "learning_rate": 6.849210730229846e-06,
+      "loss": 0.8775,
+      "step": 1550
+    },
+    {
+      "epoch": 1.9595835884874464,
+      "grad_norm": 0.7976605652572579,
+      "learning_rate": 6.669034296168855e-06,
+      "loss": 0.8751,
+      "step": 1600
+    },
+    {
+      "epoch": 2.020820575627679,
+      "grad_norm": 0.7958737424052013,
+      "learning_rate": 6.486384253156014e-06,
+      "loss": 0.8579,
+      "step": 1650
+    },
+    {
+      "epoch": 2.0820575627679117,
+      "grad_norm": 0.8331069734198607,
+      "learning_rate": 6.301531299512195e-06,
+      "loss": 0.837,
+      "step": 1700
+    },
+    {
+      "epoch": 2.1432945499081444,
+      "grad_norm": 0.7511629331953945,
+      "learning_rate": 6.11474939840398e-06,
+      "loss": 0.8327,
+      "step": 1750
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 4080,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 250,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 534961795891200.0,
+  "train_batch_size": 48,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:177f7284d8988303972d8deb70f69edb70868d890240ad46b306dcc6855a071e
+size 7224

zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)