| { | |
| "results": { | |
| "agieval": { | |
| "acc,none": 0.4384373488147073, | |
| "acc_stderr,none": 0.005138774874733036, | |
| "alias": "agieval" | |
| }, | |
| "agieval_aqua_rat": { | |
| "alias": " - agieval_aqua_rat", | |
| "acc,none": 0.40551181102362205, | |
| "acc_stderr,none": 0.030868328175712653, | |
| "acc_norm,none": 0.38976377952755903, | |
| "acc_norm_stderr,none": 0.030661222674142036 | |
| }, | |
| "agieval_gaokao_biology": { | |
| "alias": " - agieval_gaokao_biology", | |
| "acc,none": 0.48095238095238096, | |
| "acc_stderr,none": 0.034560617865111484, | |
| "acc_norm,none": 0.4714285714285714, | |
| "acc_norm_stderr,none": 0.03452921053595503 | |
| }, | |
| "agieval_gaokao_chemistry": { | |
| "alias": " - agieval_gaokao_chemistry", | |
| "acc,none": 0.42028985507246375, | |
| "acc_stderr,none": 0.034391117954401376, | |
| "acc_norm,none": 0.3961352657004831, | |
| "acc_norm_stderr,none": 0.0340767350076416 | |
| }, | |
| "agieval_gaokao_chinese": { | |
| "alias": " - agieval_gaokao_chinese", | |
| "acc,none": 0.4186991869918699, | |
| "acc_stderr,none": 0.03151871344392194, | |
| "acc_norm,none": 0.42276422764227645, | |
| "acc_norm_stderr,none": 0.03156041407531481 | |
| }, | |
| "agieval_gaokao_english": { | |
| "alias": " - agieval_gaokao_english", | |
| "acc,none": 0.6993464052287581, | |
| "acc_stderr,none": 0.02625605383571896, | |
| "acc_norm,none": 0.738562091503268, | |
| "acc_norm_stderr,none": 0.025160998214292456 | |
| }, | |
| "agieval_gaokao_geography": { | |
| "alias": " - agieval_gaokao_geography", | |
| "acc,none": 0.5477386934673367, | |
| "acc_stderr,none": 0.03537112167025914, | |
| "acc_norm,none": 0.542713567839196, | |
| "acc_norm_stderr,none": 0.035403557368657 | |
| }, | |
| "agieval_gaokao_history": { | |
| "alias": " - agieval_gaokao_history", | |
| "acc,none": 0.4553191489361702, | |
| "acc_stderr,none": 0.03255525359340355, | |
| "acc_norm,none": 0.44680851063829785, | |
| "acc_norm_stderr,none": 0.0325005368436584 | |
| }, | |
| "agieval_gaokao_mathcloze": { | |
| "alias": " - agieval_gaokao_mathcloze", | |
| "acc,none": 0.09322033898305085, | |
| "acc_stderr,none": 0.02687901150866995 | |
| }, | |
| "agieval_gaokao_mathqa": { | |
| "alias": " - agieval_gaokao_mathqa", | |
| "acc,none": 0.32763532763532766, | |
| "acc_stderr,none": 0.025087869562833914, | |
| "acc_norm,none": 0.32763532763532766, | |
| "acc_norm_stderr,none": 0.025087869562833914 | |
| }, | |
| "agieval_gaokao_physics": { | |
| "alias": " - agieval_gaokao_physics", | |
| "acc,none": 0.48, | |
| "acc_stderr,none": 0.03541569365103447, | |
| "acc_norm,none": 0.455, | |
| "acc_norm_stderr,none": 0.03530021993753286 | |
| }, | |
| "agieval_jec_qa_ca": { | |
| "alias": " - agieval_jec_qa_ca", | |
| "acc,none": 0.5085085085085085, | |
| "acc_stderr,none": 0.01582493166517233, | |
| "acc_norm,none": 0.5105105105105106, | |
| "acc_norm_stderr,none": 0.015823726166373807 | |
| }, | |
| "agieval_jec_qa_kd": { | |
| "alias": " - agieval_jec_qa_kd", | |
| "acc,none": 0.562, | |
| "acc_stderr,none": 0.01569721001969469, | |
| "acc_norm,none": 0.553, | |
| "acc_norm_stderr,none": 0.015730176046009074 | |
| }, | |
| "agieval_logiqa_en": { | |
| "alias": " - agieval_logiqa_en", | |
| "acc,none": 0.402457757296467, | |
| "acc_stderr,none": 0.01923480462752409, | |
| "acc_norm,none": 0.4055299539170507, | |
| "acc_norm_stderr,none": 0.019258381208154273 | |
| }, | |
| "agieval_logiqa_zh": { | |
| "alias": " - agieval_logiqa_zh", | |
| "acc,none": 0.4009216589861751, | |
| "acc_stderr,none": 0.01922272222545092, | |
| "acc_norm,none": 0.40706605222734255, | |
| "acc_norm_stderr,none": 0.01926987610639943 | |
| }, | |
| "agieval_lsat_ar": { | |
| "alias": " - agieval_lsat_ar", | |
| "acc,none": 0.2217391304347826, | |
| "acc_stderr,none": 0.027451496604058916, | |
| "acc_norm,none": 0.2217391304347826, | |
| "acc_norm_stderr,none": 0.02745149660405892 | |
| }, | |
| "agieval_lsat_lr": { | |
| "alias": " - agieval_lsat_lr", | |
| "acc,none": 0.5372549019607843, | |
| "acc_stderr,none": 0.022100505922784033, | |
| "acc_norm,none": 0.49607843137254903, | |
| "acc_norm_stderr,none": 0.022161428699498387 | |
| }, | |
| "agieval_lsat_rc": { | |
| "alias": " - agieval_lsat_rc", | |
| "acc,none": 0.6654275092936803, | |
| "acc_stderr,none": 0.028822264091264625, | |
| "acc_norm,none": 0.6579925650557621, | |
| "acc_norm_stderr,none": 0.028977497019824838 | |
| }, | |
| "agieval_math": { | |
| "alias": " - agieval_math", | |
| "acc,none": 0.106, | |
| "acc_stderr,none": 0.009739551265785134 | |
| }, | |
| "agieval_sat_en": { | |
| "alias": " - agieval_sat_en", | |
| "acc,none": 0.8106796116504854, | |
| "acc_stderr,none": 0.027361908621979958, | |
| "acc_norm,none": 0.7961165048543689, | |
| "acc_norm_stderr,none": 0.028138595623668772 | |
| }, | |
| "agieval_sat_en_without_passage": { | |
| "alias": " - agieval_sat_en_without_passage", | |
| "acc,none": 0.4563106796116505, | |
| "acc_stderr,none": 0.03478794599787744, | |
| "acc_norm,none": 0.45145631067961167, | |
| "acc_norm_stderr,none": 0.03475654072342856 | |
| }, | |
| "agieval_sat_math": { | |
| "alias": " - agieval_sat_math", | |
| "acc,none": 0.5227272727272727, | |
| "acc_stderr,none": 0.03375194708230163, | |
| "acc_norm,none": 0.5, | |
| "acc_norm_stderr,none": 0.033786868919974296 | |
| } | |
| }, | |
| "groups": { | |
| "agieval": { | |
| "acc,none": 0.4384373488147073, | |
| "acc_stderr,none": 0.005138774874733036, | |
| "alias": "agieval" | |
| } | |
| }, | |
| "group_subtasks": { | |
| "agieval": [ | |
| "agieval_gaokao_biology", | |
| "agieval_gaokao_chemistry", | |
| "agieval_gaokao_chinese", | |
| "agieval_gaokao_geography", | |
| "agieval_gaokao_history", | |
| "agieval_gaokao_mathcloze", | |
| "agieval_gaokao_mathqa", | |
| "agieval_gaokao_physics", | |
| "agieval_jec_qa_ca", | |
| "agieval_jec_qa_kd", | |
| "agieval_logiqa_zh", | |
| "agieval_aqua_rat", | |
| "agieval_gaokao_english", | |
| "agieval_logiqa_en", | |
| "agieval_lsat_ar", | |
| "agieval_lsat_lr", | |
| "agieval_lsat_rc", | |
| "agieval_math", | |
| "agieval_sat_en_without_passage", | |
| "agieval_sat_en", | |
| "agieval_sat_math" | |
| ] | |
| }, | |
| "configs": { | |
| "agieval_aqua_rat": { | |
| "task": "agieval_aqua_rat", | |
| "dataset_path": "hails/agieval-aqua-rat", | |
| "test_split": "test", | |
| "doc_to_text": "{{query}}", | |
| "doc_to_target": "{{gold}}", | |
| "doc_to_choice": "{{choices}}", | |
| "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\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": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "agieval_gaokao_biology": { | |
| "task": "agieval_gaokao_biology", | |
| "dataset_path": "hails/agieval-gaokao-biology", | |
| "test_split": "test", | |
| "doc_to_text": "{{query}}", | |
| "doc_to_target": "{{gold}}", | |
| "doc_to_choice": "{{choices}}", | |
| "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\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": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "agieval_gaokao_chemistry": { | |
| "task": "agieval_gaokao_chemistry", | |
| "dataset_path": "hails/agieval-gaokao-chemistry", | |
| "test_split": "test", | |
| "doc_to_text": "{{query}}", | |
| "doc_to_target": "{{gold}}", | |
| "doc_to_choice": "{{choices}}", | |
| "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\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": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "agieval_gaokao_chinese": { | |
| "task": "agieval_gaokao_chinese", | |
| "dataset_path": "hails/agieval-gaokao-chinese", | |
| "test_split": "test", | |
| "doc_to_text": "{{query}}", | |
| "doc_to_target": "{{gold}}", | |
| "doc_to_choice": "{{choices}}", | |
| "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\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": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "agieval_gaokao_english": { | |
| "task": "agieval_gaokao_english", | |
| "dataset_path": "hails/agieval-gaokao-english", | |
| "test_split": "test", | |
| "doc_to_text": "{{query}}", | |
| "doc_to_target": "{{gold}}", | |
| "doc_to_choice": "{{choices}}", | |
| "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\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": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "agieval_gaokao_geography": { | |
| "task": "agieval_gaokao_geography", | |
| "dataset_path": "hails/agieval-gaokao-geography", | |
| "test_split": "test", | |
| "doc_to_text": "{{query}}", | |
| "doc_to_target": "{{gold}}", | |
| "doc_to_choice": "{{choices}}", | |
| "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\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": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "agieval_gaokao_history": { | |
| "task": "agieval_gaokao_history", | |
| "dataset_path": "hails/agieval-gaokao-history", | |
| "test_split": "test", | |
| "doc_to_text": "{{query}}", | |
| "doc_to_target": "{{gold}}", | |
| "doc_to_choice": "{{choices}}", | |
| "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\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": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "agieval_gaokao_mathcloze": { | |
| "task": "agieval_gaokao_mathcloze", | |
| "dataset_path": "hails/agieval-gaokao-mathcloze", | |
| "test_split": "test", | |
| "doc_to_text": "{{query}}", | |
| "doc_to_target": "{{answer}}", | |
| "process_results": "def process_results(doc: dict, results: List[str]) -> Dict[str, int]:\n candidate = results[0]\n\n gold = doc[\"answer\"]\n\n if not gold:\n print(doc, candidate, gold)\n if is_equiv(candidate, gold):\n retval = 1\n else:\n retval = 0\n\n results = {\n \"acc\": retval,\n }\n return results\n", | |
| "description": "", | |
| "target_delimiter": " ", | |
| "fewshot_delimiter": "\n\n", | |
| "num_fewshot": 0, | |
| "metric_list": [ | |
| { | |
| "metric": "acc", | |
| "aggregation": "mean", | |
| "higher_is_better": true | |
| } | |
| ], | |
| "output_type": "generate_until", | |
| "generation_kwargs": { | |
| "max_gen_toks": 32, | |
| "do_sample": false, | |
| "temperature": 0.0, | |
| "until": [ | |
| "Q:" | |
| ] | |
| }, | |
| "repeats": 1, | |
| "should_decontaminate": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "agieval_gaokao_mathqa": { | |
| "task": "agieval_gaokao_mathqa", | |
| "dataset_path": "hails/agieval-gaokao-mathqa", | |
| "test_split": "test", | |
| "doc_to_text": "{{query}}", | |
| "doc_to_target": "{{gold}}", | |
| "doc_to_choice": "{{choices}}", | |
| "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\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": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "agieval_gaokao_physics": { | |
| "task": "agieval_gaokao_physics", | |
| "dataset_path": "hails/agieval-gaokao-physics", | |
| "test_split": "test", | |
| "doc_to_text": "{{query}}", | |
| "doc_to_target": "{{gold}}", | |
| "doc_to_choice": "{{choices}}", | |
| "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\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": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "agieval_jec_qa_ca": { | |
| "task": "agieval_jec_qa_ca", | |
| "dataset_path": "hails/agieval-jec-qa-ca", | |
| "test_split": "test", | |
| "doc_to_text": "{{query}}", | |
| "doc_to_target": "{{gold}}", | |
| "doc_to_choice": "{{choices}}", | |
| "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\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": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "agieval_jec_qa_kd": { | |
| "task": "agieval_jec_qa_kd", | |
| "dataset_path": "hails/agieval-jec-qa-kd", | |
| "test_split": "test", | |
| "doc_to_text": "{{query}}", | |
| "doc_to_target": "{{gold}}", | |
| "doc_to_choice": "{{choices}}", | |
| "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\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": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "agieval_logiqa_en": { | |
| "task": "agieval_logiqa_en", | |
| "dataset_path": "hails/agieval-logiqa-en", | |
| "test_split": "test", | |
| "doc_to_text": "{{query}}", | |
| "doc_to_target": "{{gold}}", | |
| "doc_to_choice": "{{choices}}", | |
| "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\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": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "agieval_logiqa_zh": { | |
| "task": "agieval_logiqa_zh", | |
| "dataset_path": "hails/agieval-logiqa-zh", | |
| "test_split": "test", | |
| "doc_to_text": "{{query}}", | |
| "doc_to_target": "{{gold}}", | |
| "doc_to_choice": "{{choices}}", | |
| "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\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": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "agieval_lsat_ar": { | |
| "task": "agieval_lsat_ar", | |
| "dataset_path": "hails/agieval-lsat-ar", | |
| "test_split": "test", | |
| "doc_to_text": "{{query}}", | |
| "doc_to_target": "{{gold}}", | |
| "doc_to_choice": "{{choices}}", | |
| "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\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": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "agieval_lsat_lr": { | |
| "task": "agieval_lsat_lr", | |
| "dataset_path": "hails/agieval-lsat-lr", | |
| "test_split": "test", | |
| "doc_to_text": "{{query}}", | |
| "doc_to_target": "{{gold}}", | |
| "doc_to_choice": "{{choices}}", | |
| "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\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": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "agieval_lsat_rc": { | |
| "task": "agieval_lsat_rc", | |
| "dataset_path": "hails/agieval-lsat-rc", | |
| "test_split": "test", | |
| "doc_to_text": "{{query}}", | |
| "doc_to_target": "{{gold}}", | |
| "doc_to_choice": "{{choices}}", | |
| "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\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": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "agieval_math": { | |
| "task": "agieval_math", | |
| "dataset_path": "hails/agieval-math", | |
| "test_split": "test", | |
| "doc_to_text": "{{query}}", | |
| "doc_to_target": "{{answer}}", | |
| "process_results": "def process_results(doc: dict, results: List[str]) -> Dict[str, int]:\n candidate = results[0]\n\n gold = doc[\"answer\"]\n\n if not gold:\n print(doc, candidate, gold)\n if is_equiv(candidate, gold):\n retval = 1\n else:\n retval = 0\n\n results = {\n \"acc\": retval,\n }\n return results\n", | |
| "description": "", | |
| "target_delimiter": " ", | |
| "fewshot_delimiter": "\n\n", | |
| "num_fewshot": 0, | |
| "metric_list": [ | |
| { | |
| "metric": "acc", | |
| "aggregation": "mean", | |
| "higher_is_better": true | |
| } | |
| ], | |
| "output_type": "generate_until", | |
| "generation_kwargs": { | |
| "max_gen_toks": 32, | |
| "do_sample": false, | |
| "temperature": 0.0, | |
| "until": [ | |
| "Q:" | |
| ] | |
| }, | |
| "repeats": 1, | |
| "should_decontaminate": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "agieval_sat_en": { | |
| "task": "agieval_sat_en", | |
| "dataset_path": "hails/agieval-sat-en", | |
| "test_split": "test", | |
| "doc_to_text": "{{query}}", | |
| "doc_to_target": "{{gold}}", | |
| "doc_to_choice": "{{choices}}", | |
| "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\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": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "agieval_sat_en_without_passage": { | |
| "task": "agieval_sat_en_without_passage", | |
| "dataset_path": "hails/agieval-sat-en-without-passage", | |
| "test_split": "test", | |
| "doc_to_text": "{{query}}", | |
| "doc_to_target": "{{gold}}", | |
| "doc_to_choice": "{{choices}}", | |
| "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\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": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| }, | |
| "agieval_sat_math": { | |
| "task": "agieval_sat_math", | |
| "dataset_path": "hails/agieval-sat-math", | |
| "test_split": "test", | |
| "doc_to_text": "{{query}}", | |
| "doc_to_target": "{{gold}}", | |
| "doc_to_choice": "{{choices}}", | |
| "process_results": "def process_results_mcqa(doc, results):\n results = [result[0] for result in results]\n\n gold = doc[\"gold\"]\n\n acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n return {\n \"acc\": acc,\n \"acc_norm\": acc_norm,\n }\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": false, | |
| "metadata": { | |
| "version": 1.0 | |
| } | |
| } | |
| }, | |
| "versions": { | |
| "agieval": 0.0, | |
| "agieval_aqua_rat": 1.0, | |
| "agieval_gaokao_biology": 1.0, | |
| "agieval_gaokao_chemistry": 1.0, | |
| "agieval_gaokao_chinese": 1.0, | |
| "agieval_gaokao_english": 1.0, | |
| "agieval_gaokao_geography": 1.0, | |
| "agieval_gaokao_history": 1.0, | |
| "agieval_gaokao_mathcloze": 1.0, | |
| "agieval_gaokao_mathqa": 1.0, | |
| "agieval_gaokao_physics": 1.0, | |
| "agieval_jec_qa_ca": 1.0, | |
| "agieval_jec_qa_kd": 1.0, | |
| "agieval_logiqa_en": 1.0, | |
| "agieval_logiqa_zh": 1.0, | |
| "agieval_lsat_ar": 1.0, | |
| "agieval_lsat_lr": 1.0, | |
| "agieval_lsat_rc": 1.0, | |
| "agieval_math": 1.0, | |
| "agieval_sat_en": 1.0, | |
| "agieval_sat_en_without_passage": 1.0, | |
| "agieval_sat_math": 1.0 | |
| }, | |
| "n-shot": { | |
| "agieval_aqua_rat": 0, | |
| "agieval_gaokao_biology": 0, | |
| "agieval_gaokao_chemistry": 0, | |
| "agieval_gaokao_chinese": 0, | |
| "agieval_gaokao_english": 0, | |
| "agieval_gaokao_geography": 0, | |
| "agieval_gaokao_history": 0, | |
| "agieval_gaokao_mathcloze": 0, | |
| "agieval_gaokao_mathqa": 0, | |
| "agieval_gaokao_physics": 0, | |
| "agieval_jec_qa_ca": 0, | |
| "agieval_jec_qa_kd": 0, | |
| "agieval_logiqa_en": 0, | |
| "agieval_logiqa_zh": 0, | |
| "agieval_lsat_ar": 0, | |
| "agieval_lsat_lr": 0, | |
| "agieval_lsat_rc": 0, | |
| "agieval_math": 0, | |
| "agieval_sat_en": 0, | |
| "agieval_sat_en_without_passage": 0, | |
| "agieval_sat_math": 0 | |
| }, | |
| "higher_is_better": { | |
| "agieval": { | |
| "acc": true, | |
| "acc_norm": true | |
| }, | |
| "agieval_aqua_rat": { | |
| "acc": true, | |
| "acc_norm": true | |
| }, | |
| "agieval_gaokao_biology": { | |
| "acc": true, | |
| "acc_norm": true | |
| }, | |
| "agieval_gaokao_chemistry": { | |
| "acc": true, | |
| "acc_norm": true | |
| }, | |
| "agieval_gaokao_chinese": { | |
| "acc": true, | |
| "acc_norm": true | |
| }, | |
| "agieval_gaokao_english": { | |
| "acc": true, | |
| "acc_norm": true | |
| }, | |
| "agieval_gaokao_geography": { | |
| "acc": true, | |
| "acc_norm": true | |
| }, | |
| "agieval_gaokao_history": { | |
| "acc": true, | |
| "acc_norm": true | |
| }, | |
| "agieval_gaokao_mathcloze": { | |
| "acc": true | |
| }, | |
| "agieval_gaokao_mathqa": { | |
| "acc": true, | |
| "acc_norm": true | |
| }, | |
| "agieval_gaokao_physics": { | |
| "acc": true, | |
| "acc_norm": true | |
| }, | |
| "agieval_jec_qa_ca": { | |
| "acc": true, | |
| "acc_norm": true | |
| }, | |
| "agieval_jec_qa_kd": { | |
| "acc": true, | |
| "acc_norm": true | |
| }, | |
| "agieval_logiqa_en": { | |
| "acc": true, | |
| "acc_norm": true | |
| }, | |
| "agieval_logiqa_zh": { | |
| "acc": true, | |
| "acc_norm": true | |
| }, | |
| "agieval_lsat_ar": { | |
| "acc": true, | |
| "acc_norm": true | |
| }, | |
| "agieval_lsat_lr": { | |
| "acc": true, | |
| "acc_norm": true | |
| }, | |
| "agieval_lsat_rc": { | |
| "acc": true, | |
| "acc_norm": true | |
| }, | |
| "agieval_math": { | |
| "acc": true | |
| }, | |
| "agieval_sat_en": { | |
| "acc": true, | |
| "acc_norm": true | |
| }, | |
| "agieval_sat_en_without_passage": { | |
| "acc": true, | |
| "acc_norm": true | |
| }, | |
| "agieval_sat_math": { | |
| "acc": true, | |
| "acc_norm": true | |
| } | |
| }, | |
| "n-samples": { | |
| "agieval_gaokao_biology": { | |
| "original": 210, | |
| "effective": 210 | |
| }, | |
| "agieval_gaokao_chemistry": { | |
| "original": 207, | |
| "effective": 207 | |
| }, | |
| "agieval_gaokao_chinese": { | |
| "original": 246, | |
| "effective": 246 | |
| }, | |
| "agieval_gaokao_geography": { | |
| "original": 199, | |
| "effective": 199 | |
| }, | |
| "agieval_gaokao_history": { | |
| "original": 235, | |
| "effective": 235 | |
| }, | |
| "agieval_gaokao_mathcloze": { | |
| "original": 118, | |
| "effective": 118 | |
| }, | |
| "agieval_gaokao_mathqa": { | |
| "original": 351, | |
| "effective": 351 | |
| }, | |
| "agieval_gaokao_physics": { | |
| "original": 200, | |
| "effective": 200 | |
| }, | |
| "agieval_jec_qa_ca": { | |
| "original": 999, | |
| "effective": 999 | |
| }, | |
| "agieval_jec_qa_kd": { | |
| "original": 1000, | |
| "effective": 1000 | |
| }, | |
| "agieval_logiqa_zh": { | |
| "original": 651, | |
| "effective": 651 | |
| }, | |
| "agieval_aqua_rat": { | |
| "original": 254, | |
| "effective": 254 | |
| }, | |
| "agieval_gaokao_english": { | |
| "original": 306, | |
| "effective": 306 | |
| }, | |
| "agieval_logiqa_en": { | |
| "original": 651, | |
| "effective": 651 | |
| }, | |
| "agieval_lsat_ar": { | |
| "original": 230, | |
| "effective": 230 | |
| }, | |
| "agieval_lsat_lr": { | |
| "original": 510, | |
| "effective": 510 | |
| }, | |
| "agieval_lsat_rc": { | |
| "original": 269, | |
| "effective": 269 | |
| }, | |
| "agieval_math": { | |
| "original": 1000, | |
| "effective": 1000 | |
| }, | |
| "agieval_sat_en_without_passage": { | |
| "original": 206, | |
| "effective": 206 | |
| }, | |
| "agieval_sat_en": { | |
| "original": 206, | |
| "effective": 206 | |
| }, | |
| "agieval_sat_math": { | |
| "original": 220, | |
| "effective": 220 | |
| } | |
| }, | |
| "config": { | |
| "model": "hf", | |
| "model_args": "pretrained=tiiuae/Falcon3-7B-Instruct,trust_remote_code=True,cache_dir=/tmp,parallelize=True", | |
| "model_num_parameters": 7455550464, | |
| "model_dtype": "torch.bfloat16", | |
| "model_revision": "main", | |
| "model_sha": "5563a370c1848366c7a095bde4bbff2cdb419cc6", | |
| "batch_size": 1, | |
| "batch_sizes": [], | |
| "device": null, | |
| "use_cache": null, | |
| "limit": null, | |
| "bootstrap_iters": 100000, | |
| "gen_kwargs": null, | |
| "random_seed": 0, | |
| "numpy_seed": 1234, | |
| "torch_seed": 1234, | |
| "fewshot_seed": 1234 | |
| }, | |
| "git_hash": "5e10e017", | |
| "date": 1736906617.337926, | |
| "pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 22.04.3 LTS (x86_64)\nGCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\nClang version: Could not collect\nCMake version: version 3.27.1\nLibc version: glibc-2.35\n\nPython version: 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-1064-azure-x86_64-with-glibc2.35\nIs CUDA available: True\nCUDA runtime version: 12.2.128\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100-SXM4-80GB\nGPU 1: NVIDIA A100-SXM4-80GB\nGPU 2: NVIDIA A100-SXM4-80GB\nGPU 3: NVIDIA A100-SXM4-80GB\nGPU 4: NVIDIA A100-SXM4-80GB\nGPU 5: NVIDIA A100-SXM4-80GB\nGPU 6: NVIDIA A100-SXM4-80GB\nGPU 7: NVIDIA A100-SXM4-80GB\n\nNvidia driver version: 535.161.08\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.4\n/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.4\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: 48 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 96\nOn-line CPU(s) list: 0-95\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7V12 64-Core Processor\nCPU family: 23\nModel: 49\nThread(s) per core: 1\nCore(s) per socket: 48\nSocket(s): 2\nStepping: 0\nBogoMIPS: 4890.88\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core ssbd vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid\nHypervisor vendor: Microsoft\nVirtualization type: full\nL1d cache: 3 MiB (96 instances)\nL1i cache: 3 MiB (96 instances)\nL2 cache: 48 MiB (96 instances)\nL3 cache: 384 MiB (24 instances)\nNUMA node(s): 4\nNUMA node0 CPU(s): 0-23\nNUMA node1 CPU(s): 24-47\nNUMA node2 CPU(s): 48-71\nNUMA node3 CPU(s): 72-95\nVulnerability Gather data sampling: Not affected\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: Mitigation; untrained return thunk; SMT disabled\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\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; Retpolines; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected\nVulnerability Srbds: Not affected\nVulnerability Tsx async abort: Not affected\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] onnx==1.14.0\n[pip3] pytorch-lightning==2.0.7\n[pip3] pytorch-quantization==2.1.2\n[pip3] torch==2.4.0\n[pip3] torch-tensorrt==2.0.0.dev0\n[pip3] torchaudio==2.1.0\n[pip3] torchdata==0.7.0a0\n[pip3] torchmetrics==1.2.0\n[pip3] torchvision==0.19.0\n[pip3] triton==3.0.0\n[conda] Could not collect", | |
| "transformers_version": "4.48.0", | |
| "upper_git_hash": "f64fe2f2a86055aaecced603b56097fd79201711", | |
| "tokenizer_pad_token": [ | |
| "<|pad|>", | |
| "2023" | |
| ], | |
| "tokenizer_eos_token": [ | |
| "<|endoftext|>", | |
| "11" | |
| ], | |
| "tokenizer_bos_token": [ | |
| null, | |
| "None" | |
| ], | |
| "eot_token_id": 11, | |
| "max_length": 32768, | |
| "task_hashes": { | |
| "agieval_gaokao_biology": "19067f814ce4acb5c8b4db09600249eb11928dfeaabfb29026fbcc5aeae9bf6e", | |
| "agieval_gaokao_chemistry": "2aeca40c247a4384598991ab7645d5d337bd76947d4c5256933e210a01b2b73c", | |
| "agieval_gaokao_chinese": "11a6a9f458b461a70acda2dd2f424c7f68430c0ab9d8b1a62655e01cedda7fbe", | |
| "agieval_gaokao_geography": "16f33d14fe56d3b156071286a973d378fdc31d2953e97910506a74ffa9deb726", | |
| "agieval_gaokao_history": "812ddb5af1d5ee5b792434865d543e48911ac58dd98f58b28a1e55ebbd899933", | |
| "agieval_gaokao_mathcloze": "75ecfccf5d9d01dcae7593e210c755e953d0f9e76634565a62fe40a4c08b02d7", | |
| "agieval_gaokao_mathqa": "1a62d808a5c27751c285ba7f0d111de21b7bceddb3f180f2e12ea864ba0e3f21", | |
| "agieval_gaokao_physics": "c4dca484c75b47142e23919123632aa6da66b7e4a5ea6cce3a5d2cf834039312", | |
| "agieval_jec_qa_ca": "dc63435e7da4ca4da0c86837082ae6c95ae4f5e868a6e2e8e8c388fdb292829c", | |
| "agieval_jec_qa_kd": "a60a905d40fceb91c419e45b42cc80f77ac0c8b2154795a3c27ea2c8717843da", | |
| "agieval_logiqa_zh": "064313b20368e01816c3222904da40cd36813d6ce3a10492074f3134dd1e9a25", | |
| "agieval_aqua_rat": "590732bf8f23653400bcc45709ef3aa17cc1eaa69d228cc1eabb11bd1b48600d", | |
| "agieval_gaokao_english": "308d1ba44ed10ddf2626ace40f23a0700e31b7ca361fb77d683d103b9ab653ff", | |
| "agieval_logiqa_en": "1a372f08810b63ad9abe4766c1ab68fd24f0a86f7604f08f32127bde985d9c29", | |
| "agieval_lsat_ar": "177ca1fa872eb6221c8d697a1c6c49d44ca6989d11688348360bfbb9af5bb3dc", | |
| "agieval_lsat_lr": "50bb8b6c692ee86cfab3e6b4617b246fb654c713ebd438497d11008626ee5cef", | |
| "agieval_lsat_rc": "9c404a0b73f50b3f71b611aa3cf5d65542d5faad568abf9d85c41404504290a7", | |
| "agieval_math": "846f11659e5b8569f30b18c66e21dc1b40368bf041133d68d5523dac0ae27853", | |
| "agieval_sat_en_without_passage": "b249ac869804c4f6b1884c5b855302fab9acb3e9cad970c0398681ed514a38a2", | |
| "agieval_sat_en": "86c34b77b2f5ea8353df8dabe480afcc613505e96de27ffd7aa132a9d725d6eb", | |
| "agieval_sat_math": "1f5c90ed7628a8f9a0ea8a08290595417e73f3793e131a2aa13e9b3f62aa4798" | |
| }, | |
| "model_source": "hf", | |
| "model_name": "tiiuae/Falcon3-7B-Instruct", | |
| "model_name_sanitized": "tiiuae__Falcon3-7B-Instruct", | |
| "system_instruction": null, | |
| "system_instruction_sha": null, | |
| "fewshot_as_multiturn": false, | |
| "chat_template": null, | |
| "chat_template_sha": null, | |
| "start_time": 616867.569233521, | |
| "end_time": 617195.20891048, | |
| "total_evaluation_time_seconds": "327.639676959021" | |
| } |