{ "results": { "culpa-dolore-9940_logiqa2_base": { "alias": "culpa-dolore-9940_logiqa2_base", "acc,none": 0.522264631043257, "acc_stderr,none": 0.012602331890057493 }, "culpa-dolore-9940_logiqa_base": { "alias": "culpa-dolore-9940_logiqa_base", "acc,none": 0.3977635782747604, "acc_stderr,none": 0.019577444739201977 }, "culpa-dolore-9940_lsat-ar_base": { "alias": "culpa-dolore-9940_lsat-ar_base", "acc,none": 0.2956521739130435, "acc_stderr,none": 0.030155489768916185 }, "culpa-dolore-9940_lsat-lr_base": { "alias": "culpa-dolore-9940_lsat-lr_base", "acc,none": 0.5647058823529412, "acc_stderr,none": 0.021975747875185716 }, "culpa-dolore-9940_lsat-rc_base": { "alias": "culpa-dolore-9940_lsat-rc_base", "acc,none": 0.5799256505576208, "acc_stderr,none": 0.030149620080212 } }, "group_subtasks": { "culpa-dolore-9940_logiqa2_base": [], "culpa-dolore-9940_logiqa_base": [], "culpa-dolore-9940_lsat-ar_base": [], "culpa-dolore-9940_lsat-lr_base": [], "culpa-dolore-9940_lsat-rc_base": [] }, "configs": { "culpa-dolore-9940_logiqa2_base": { "task": "culpa-dolore-9940_logiqa2_base", "tag": "logikon-bench", "group": "logikon-bench", "dataset_path": "cot-leaderboard/cot-eval-traces-2.0", "dataset_kwargs": { "data_files": { "test": "data/Qwen/Qwen2.5-32B-Instruct/culpa-dolore-9940-logiqa2.parquet" } }, "test_split": "test", "doc_to_text": "def doc_to_text(doc) -> str:\n \"\"\"\n Answer the following question about the given passage.\n \n Passage: \n \n Question: \n A. \n B. \n C. \n D. \n [E. ]\n \n Answer:\n \"\"\"\n k = len(doc[\"options\"])\n choices = [\"a\", \"b\", \"c\", \"d\", \"e\"][:k]\n prompt = \"Answer the following question about the given passage.\\n\\n\"\n prompt = \"Passage: \" + doc[\"passage\"] + \"\\n\\n\"\n prompt += \"Question: \" + doc[\"question\"] + \"\\n\"\n for choice, option in zip(choices, doc[\"options\"]):\n prompt += f\"{choice.upper()}. {option}\\n\"\n prompt += \"\\n\"\n prompt += \"Answer:\"\n return prompt\n", "doc_to_target": "{{answer}}", "doc_to_choice": "{{options}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\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 } }, "culpa-dolore-9940_logiqa_base": { "task": "culpa-dolore-9940_logiqa_base", "tag": "logikon-bench", "group": "logikon-bench", "dataset_path": "cot-leaderboard/cot-eval-traces-2.0", "dataset_kwargs": { "data_files": { "test": "data/Qwen/Qwen2.5-32B-Instruct/culpa-dolore-9940-logiqa.parquet" } }, "test_split": "test", "doc_to_text": "def doc_to_text(doc) -> str:\n \"\"\"\n Answer the following question about the given passage.\n \n Passage: \n \n Question: \n A. \n B. \n C. \n D. \n [E. ]\n \n Answer:\n \"\"\"\n k = len(doc[\"options\"])\n choices = [\"a\", \"b\", \"c\", \"d\", \"e\"][:k]\n prompt = \"Answer the following question about the given passage.\\n\\n\"\n prompt = \"Passage: \" + doc[\"passage\"] + \"\\n\\n\"\n prompt += \"Question: \" + doc[\"question\"] + \"\\n\"\n for choice, option in zip(choices, doc[\"options\"]):\n prompt += f\"{choice.upper()}. {option}\\n\"\n prompt += \"\\n\"\n prompt += \"Answer:\"\n return prompt\n", "doc_to_target": "{{answer}}", "doc_to_choice": "{{options}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\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 } }, "culpa-dolore-9940_lsat-ar_base": { "task": "culpa-dolore-9940_lsat-ar_base", "tag": "logikon-bench", "group": "logikon-bench", "dataset_path": "cot-leaderboard/cot-eval-traces-2.0", "dataset_kwargs": { "data_files": { "test": "data/Qwen/Qwen2.5-32B-Instruct/culpa-dolore-9940-lsat-ar.parquet" } }, "test_split": "test", "doc_to_text": "def doc_to_text(doc) -> str:\n \"\"\"\n Answer the following question about the given passage.\n \n Passage: \n \n Question: \n A. \n B. \n C. \n D. \n [E. ]\n \n Answer:\n \"\"\"\n k = len(doc[\"options\"])\n choices = [\"a\", \"b\", \"c\", \"d\", \"e\"][:k]\n prompt = \"Answer the following question about the given passage.\\n\\n\"\n prompt = \"Passage: \" + doc[\"passage\"] + \"\\n\\n\"\n prompt += \"Question: \" + doc[\"question\"] + \"\\n\"\n for choice, option in zip(choices, doc[\"options\"]):\n prompt += f\"{choice.upper()}. {option}\\n\"\n prompt += \"\\n\"\n prompt += \"Answer:\"\n return prompt\n", "doc_to_target": "{{answer}}", "doc_to_choice": "{{options}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\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 } }, "culpa-dolore-9940_lsat-lr_base": { "task": "culpa-dolore-9940_lsat-lr_base", "tag": "logikon-bench", "group": "logikon-bench", "dataset_path": "cot-leaderboard/cot-eval-traces-2.0", "dataset_kwargs": { "data_files": { "test": "data/Qwen/Qwen2.5-32B-Instruct/culpa-dolore-9940-lsat-lr.parquet" } }, "test_split": "test", "doc_to_text": "def doc_to_text(doc) -> str:\n \"\"\"\n Answer the following question about the given passage.\n \n Passage: \n \n Question: \n A. \n B. \n C. \n D. \n [E. ]\n \n Answer:\n \"\"\"\n k = len(doc[\"options\"])\n choices = [\"a\", \"b\", \"c\", \"d\", \"e\"][:k]\n prompt = \"Answer the following question about the given passage.\\n\\n\"\n prompt = \"Passage: \" + doc[\"passage\"] + \"\\n\\n\"\n prompt += \"Question: \" + doc[\"question\"] + \"\\n\"\n for choice, option in zip(choices, doc[\"options\"]):\n prompt += f\"{choice.upper()}. {option}\\n\"\n prompt += \"\\n\"\n prompt += \"Answer:\"\n return prompt\n", "doc_to_target": "{{answer}}", "doc_to_choice": "{{options}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\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 } }, "culpa-dolore-9940_lsat-rc_base": { "task": "culpa-dolore-9940_lsat-rc_base", "tag": "logikon-bench", "group": "logikon-bench", "dataset_path": "cot-leaderboard/cot-eval-traces-2.0", "dataset_kwargs": { "data_files": { "test": "data/Qwen/Qwen2.5-32B-Instruct/culpa-dolore-9940-lsat-rc.parquet" } }, "test_split": "test", "doc_to_text": "def doc_to_text(doc) -> str:\n \"\"\"\n Answer the following question about the given passage.\n \n Passage: \n \n Question: \n A. \n B. \n C. \n D. \n [E. ]\n \n Answer:\n \"\"\"\n k = len(doc[\"options\"])\n choices = [\"a\", \"b\", \"c\", \"d\", \"e\"][:k]\n prompt = \"Answer the following question about the given passage.\\n\\n\"\n prompt = \"Passage: \" + doc[\"passage\"] + \"\\n\\n\"\n prompt += \"Question: \" + doc[\"question\"] + \"\\n\"\n for choice, option in zip(choices, doc[\"options\"]):\n prompt += f\"{choice.upper()}. {option}\\n\"\n prompt += \"\\n\"\n prompt += \"Answer:\"\n return prompt\n", "doc_to_target": "{{answer}}", "doc_to_choice": "{{options}}", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\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": { "culpa-dolore-9940_logiqa2_base": 0.0, "culpa-dolore-9940_logiqa_base": 0.0, "culpa-dolore-9940_lsat-ar_base": 0.0, "culpa-dolore-9940_lsat-lr_base": 0.0, "culpa-dolore-9940_lsat-rc_base": 0.0 }, "n-shot": { "culpa-dolore-9940_logiqa2_base": 0, "culpa-dolore-9940_logiqa_base": 0, "culpa-dolore-9940_lsat-ar_base": 0, "culpa-dolore-9940_lsat-lr_base": 0, "culpa-dolore-9940_lsat-rc_base": 0 }, "higher_is_better": { "culpa-dolore-9940_logiqa2_base": { "acc": true }, "culpa-dolore-9940_logiqa_base": { "acc": true }, "culpa-dolore-9940_lsat-ar_base": { "acc": true }, "culpa-dolore-9940_lsat-lr_base": { "acc": true }, "culpa-dolore-9940_lsat-rc_base": { "acc": true } }, "n-samples": { "culpa-dolore-9940_lsat-rc_base": { "original": 269, "effective": 269 }, "culpa-dolore-9940_lsat-lr_base": { "original": 510, "effective": 510 }, "culpa-dolore-9940_lsat-ar_base": { "original": 230, "effective": 230 }, "culpa-dolore-9940_logiqa_base": { "original": 626, "effective": 626 }, "culpa-dolore-9940_logiqa2_base": { "original": 1572, "effective": 1572 } }, "config": { "model": "local-completions", "model_args": "base_url=http://localhost:8080/v1/completions,num_concurrent=1,max_retries=3,tokenized_requests=False,model=Qwen/Qwen2.5-32B-Instruct,trust_remote_code=True", "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": "d7733d8", "date": 1727917670.2146919, "pretty_env_info": "PyTorch version: 2.4.1+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Red Hat Enterprise Linux release 8.8 (Ootpa) (x86_64)\nGCC version: (GCC) 8.5.0 20210514 (Red Hat 8.5.0-18)\nClang version: Could not collect\nCMake version: version 3.20.2\nLibc version: glibc-2.28\n\nPython version: 3.11.2 (main, May 20 2024, 08:58:58) [GCC 8.5.0 20210514 (Red Hat 8.5.0-18)] (64-bit runtime)\nPython platform: Linux-4.18.0-477.70.1.el8_8.x86_64-x86_64-with-glibc2.28\nIs CUDA available: True\nCUDA runtime version: 12.2.140\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA H100\nGPU 1: NVIDIA H100\n\nNvidia driver version: 550.54.15\ncuDNN version: Probably one of the following:\n/hkfs/home/software/all/devel/cuda/11.2/targets/x86_64-linux/lib/libcudnn.so.8.1.1\n/hkfs/home/software/all/devel/cuda/11.2/targets/x86_64-linux/lib/libcudnn_adv_infer.so.8.1.1\n/hkfs/home/software/all/devel/cuda/11.2/targets/x86_64-linux/lib/libcudnn_adv_train.so.8.1.1\n/hkfs/home/software/all/devel/cuda/11.2/targets/x86_64-linux/lib/libcudnn_cnn_infer.so.8.1.1\n/hkfs/home/software/all/devel/cuda/11.2/targets/x86_64-linux/lib/libcudnn_cnn_train.so.8.1.1\n/hkfs/home/software/all/devel/cuda/11.2/targets/x86_64-linux/lib/libcudnn_ops_infer.so.8.1.1\n/hkfs/home/software/all/devel/cuda/11.2/targets/x86_64-linux/lib/libcudnn_ops_train.so.8.1.1\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\n\nCPU:\nArchitektur: x86_64\nCPU Operationsmodus: 32-bit, 64-bit\nByte-Reihenfolge: Little Endian\nCPU(s): 128\nListe der Online-CPU(s): 0-127\nThread(s) pro Kern: 2\nKern(e) pro Socket: 32\nSockel: 2\nNUMA-Knoten: 2\nAnbieterkennung: AuthenticAMD\nProzessorfamilie: 25\nModell: 17\nModellname: AMD EPYC 9354 32-Core Processor\nStepping: 1\nCPU MHz: 3800.000\nMaximale Taktfrequenz der CPU: 3800,0000\nMinimale Taktfrequenz der CPU: 400,0000\nBogoMIPS: 6500.59\nVirtualisierung: AMD-V\nL1d Cache: 32K\nL1i Cache: 32K\nL2 Cache: 1024K\nL3 Cache: 32768K\nNUMA-Knoten0 CPU(s): 0-31,64-95\nNUMA-Knoten1 CPU(s): 32-63,96-127\nMarkierungen: 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 nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 invpcid_single hw_pstate ssbd mba perfmon_v2 ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local avx512_bf16 clzero irperf xsaveerptr wbnoinvd amd_ppin cppc arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif v_spec_ctrl avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid overflow_recov succor smca fsrm flush_l1d\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] torch==2.4.1\n[pip3] triton==3.0.0\n[conda] Could not collect", "transformers_version": "4.45.1", "upper_git_hash": null, "tokenizer_pad_token": [ "<|endoftext|>", "151643" ], "tokenizer_eos_token": [ "<|im_end|>", "151645" ], "tokenizer_bos_token": [ null, "None" ], "eot_token_id": 151645, "max_length": 2047, "task_hashes": {}, "model_source": "local-completions", "model_name": "Qwen/Qwen2.5-32B-Instruct", "model_name_sanitized": "Qwen__Qwen2.5-32B-Instruct", "system_instruction": null, "system_instruction_sha": null, "fewshot_as_multiturn": false, "chat_template": null, "chat_template_sha": null, "start_time": 239636.574422539, "end_time": 240426.545343983, "total_evaluation_time_seconds": "789.970921443979" }