{ "results": { "saepe-dolor-2147_lsat-rc_base": { "acc,none": 0.6133828996282528, "acc_stderr,none": 0.029746711725453002, "alias": "saepe-dolor-2147_lsat-rc_base" }, "saepe-dolor-2147_lsat-lr_base": { "acc,none": 0.5882352941176471, "acc_stderr,none": 0.02181429628344194, "alias": "saepe-dolor-2147_lsat-lr_base" }, "saepe-dolor-2147_lsat-ar_base": { "acc,none": 0.2956521739130435, "acc_stderr,none": 0.03015548976891618, "alias": "saepe-dolor-2147_lsat-ar_base" }, "saepe-dolor-2147_logiqa_base": { "acc,none": 0.41373801916932906, "acc_stderr,none": 0.019700106422582242, "alias": "saepe-dolor-2147_logiqa_base" }, "saepe-dolor-2147_logiqa2_base": { "acc,none": 0.5521628498727735, "acc_stderr,none": 0.012546007936599718, "alias": "saepe-dolor-2147_logiqa2_base" } }, "group_subtasks": { "saepe-dolor-2147_logiqa2_base": [], "saepe-dolor-2147_logiqa_base": [], "saepe-dolor-2147_lsat-ar_base": [], "saepe-dolor-2147_lsat-lr_base": [], "saepe-dolor-2147_lsat-rc_base": [] }, "configs": { "saepe-dolor-2147_logiqa2_base": { "task": "saepe-dolor-2147_logiqa2_base", "group": "logikon-bench", "dataset_path": "cot-leaderboard/cot-eval-traces-2.0", "dataset_kwargs": { "data_files": { "test": "data/meta-llama/Meta-Llama-3.1-70B-Instruct/saepe-dolor-2147-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 } }, "saepe-dolor-2147_logiqa_base": { "task": "saepe-dolor-2147_logiqa_base", "group": "logikon-bench", "dataset_path": "cot-leaderboard/cot-eval-traces-2.0", "dataset_kwargs": { "data_files": { "test": "data/meta-llama/Meta-Llama-3.1-70B-Instruct/saepe-dolor-2147-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 } }, "saepe-dolor-2147_lsat-ar_base": { "task": "saepe-dolor-2147_lsat-ar_base", "group": "logikon-bench", "dataset_path": "cot-leaderboard/cot-eval-traces-2.0", "dataset_kwargs": { "data_files": { "test": "data/meta-llama/Meta-Llama-3.1-70B-Instruct/saepe-dolor-2147-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 } }, "saepe-dolor-2147_lsat-lr_base": { "task": "saepe-dolor-2147_lsat-lr_base", "group": "logikon-bench", "dataset_path": "cot-leaderboard/cot-eval-traces-2.0", "dataset_kwargs": { "data_files": { "test": "data/meta-llama/Meta-Llama-3.1-70B-Instruct/saepe-dolor-2147-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 } }, "saepe-dolor-2147_lsat-rc_base": { "task": "saepe-dolor-2147_lsat-rc_base", "group": "logikon-bench", "dataset_path": "cot-leaderboard/cot-eval-traces-2.0", "dataset_kwargs": { "data_files": { "test": "data/meta-llama/Meta-Llama-3.1-70B-Instruct/saepe-dolor-2147-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": { "saepe-dolor-2147_logiqa2_base": 0.0, "saepe-dolor-2147_logiqa_base": 0.0, "saepe-dolor-2147_lsat-ar_base": 0.0, "saepe-dolor-2147_lsat-lr_base": 0.0, "saepe-dolor-2147_lsat-rc_base": 0.0 }, "n-shot": { "saepe-dolor-2147_logiqa2_base": 0, "saepe-dolor-2147_logiqa_base": 0, "saepe-dolor-2147_lsat-ar_base": 0, "saepe-dolor-2147_lsat-lr_base": 0, "saepe-dolor-2147_lsat-rc_base": 0 }, "higher_is_better": { "saepe-dolor-2147_logiqa2_base": { "acc": true }, "saepe-dolor-2147_logiqa_base": { "acc": true }, "saepe-dolor-2147_lsat-ar_base": { "acc": true }, "saepe-dolor-2147_lsat-lr_base": { "acc": true }, "saepe-dolor-2147_lsat-rc_base": { "acc": true } }, "n-samples": { "saepe-dolor-2147_lsat-rc_base": { "original": 269, "effective": 269 }, "saepe-dolor-2147_lsat-lr_base": { "original": 510, "effective": 510 }, "saepe-dolor-2147_lsat-ar_base": { "original": 230, "effective": 230 }, "saepe-dolor-2147_logiqa_base": { "original": 626, "effective": 626 }, "saepe-dolor-2147_logiqa2_base": { "original": 1572, "effective": 1572 } }, "config": { "model": "vllm", "model_args": "pretrained=meta-llama/Meta-Llama-3.1-70B-Instruct,revision=main,dtype=bfloat16,tensor_parallel_size=8,gpu_memory_utilization=0.7,trust_remote_code=true,max_length=2048", "batch_size": "auto", "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": "4d6d2d8", "date": 1725902286.229745, "pretty_env_info": "PyTorch version: 2.3.1+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\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-4.18.0-477.51.1.el8_8.x86_64-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 A100-SXM4-40GB\nGPU 1: NVIDIA A100-SXM4-40GB\nGPU 2: NVIDIA A100-SXM4-40GB\nGPU 3: NVIDIA A100-SXM4-40GB\nGPU 4: NVIDIA A100-SXM4-40GB\nGPU 5: NVIDIA A100-SXM4-40GB\nGPU 6: NVIDIA A100-SXM4-40GB\nGPU 7: NVIDIA A100-SXM4-40GB\n\nNvidia driver version: 550.54.15\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: 43 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 256\nOn-line CPU(s) list: 0-255\nVendor ID: AuthenticAMD\nModel name: AMD EPYC 7742 64-Core Processor\nCPU family: 23\nModel: 49\nThread(s) per core: 2\nCore(s) per socket: 64\nSocket(s): 2\nStepping: 0\nFrequency boost: enabled\nCPU max MHz: 2250.0000\nCPU min MHz: 1500.0000\nBogoMIPS: 4491.74\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 nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq monitor ssse3 fma cx16 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 hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr wbnoinvd arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif v_spec_ctrl umip rdpid overflow_recov succor smca sme sev sev_es\nVirtualization: AMD-V\nL1d cache: 4 MiB (128 instances)\nL1i cache: 4 MiB (128 instances)\nL2 cache: 64 MiB (128 instances)\nL3 cache: 512 MiB (32 instances)\nNUMA node(s): 8\nNUMA node0 CPU(s): 0-15,128-143\nNUMA node1 CPU(s): 16-31,144-159\nNUMA node2 CPU(s): 32-47,160-175\nNUMA node3 CPU(s): 48-63,176-191\nNUMA node4 CPU(s): 64-79,192-207\nNUMA node5 CPU(s): 80-95,208-223\nNUMA node6 CPU(s): 96-111,224-239\nNUMA node7 CPU(s): 112-127,240-255\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 enabled with STIBP protection\nVulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl\nVulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2: Mitigation; Retpolines, IBPB conditional, STIBP always-on, RSB filling, PBRSB-eIBRS Not affected\nVulnerability Srbds: Not affected\nVulnerability Tsx async abort: Not affected\n\nVersions of relevant libraries:\n[pip3] flashinfer==0.1.3+cu121torch2.3\n[pip3] mypy-extensions==1.0.0\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==2.3.1\n[pip3] torch-tensorrt==2.4.0a0\n[pip3] torchvision==0.18.1\n[pip3] triton==2.3.1\n[conda] Could not collect", "transformers_version": "4.43.3", "upper_git_hash": null, "tokenizer_pad_token": [ "<|eot_id|>", 128009 ], "tokenizer_eos_token": [ "<|eot_id|>", 128009 ], "tokenizer_bos_token": [ "<|begin_of_text|>", 128000 ], "eot_token_id": 128009, "max_length": 2048, "task_hashes": {}, "model_source": "vllm", "model_name": "meta-llama/Meta-Llama-3.1-70B-Instruct", "model_name_sanitized": "meta-llama__Meta-Llama-3.1-70B-Instruct", "system_instruction": null, "system_instruction_sha": null, "fewshot_as_multiturn": false, "chat_template": null, "chat_template_sha": null, "start_time": 7709602.0604163, "end_time": 7710264.573935508, "total_evaluation_time_seconds": "662.513519207947" }