Upload results for model meta-llama/Meta-Llama-3.1-70B-Instruct

data/meta-llama/Meta-Llama-3.1-70B-Instruct/cot/24-09-09-19:06:49_idx25/meta-llama__Meta-Llama-3.1-70B-Instruct/results_2024-09-09T22-07-35.408180.json

@@ -0,0 +1,292 @@
+{
+  "results": {
+    "repudiandae-autem-9860_lsat-rc_cot": {
+      "acc,none": 0.8475836431226765,
+      "acc_stderr,none": 0.021955315121071482,
+      "alias": "repudiandae-autem-9860_lsat-rc_cot"
+    },
+    "repudiandae-autem-9860_lsat-lr_cot": {
+      "acc,none": 0.711764705882353,
+      "acc_stderr,none": 0.020076264678059532,
+      "alias": "repudiandae-autem-9860_lsat-lr_cot"
+    },
+    "repudiandae-autem-9860_lsat-ar_cot": {
+      "acc,none": 0.26956521739130435,
+      "acc_stderr,none": 0.02932276422894953,
+      "alias": "repudiandae-autem-9860_lsat-ar_cot"
+    },
+    "repudiandae-autem-9860_logiqa_cot": {
+      "acc,none": 0.41214057507987223,
+      "acc_stderr,none": 0.01968880784416188,
+      "alias": "repudiandae-autem-9860_logiqa_cot"
+    },
+    "repudiandae-autem-9860_logiqa2_cot": {
+      "acc,none": 0.6005089058524173,
+      "acc_stderr,none": 0.012357345371236998,
+      "alias": "repudiandae-autem-9860_logiqa2_cot"
+    }
+  },
+  "group_subtasks": {
+    "repudiandae-autem-9860_logiqa2_cot": [],
+    "repudiandae-autem-9860_logiqa_cot": [],
+    "repudiandae-autem-9860_lsat-ar_cot": [],
+    "repudiandae-autem-9860_lsat-lr_cot": [],
+    "repudiandae-autem-9860_lsat-rc_cot": []
+  },
+  "configs": {
+    "repudiandae-autem-9860_logiqa2_cot": {
+      "task": "repudiandae-autem-9860_logiqa2_cot",
+      "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/repudiandae-autem-9860-logiqa2.parquet"
+        }
+      },
+      "test_split": "test",
+      "doc_to_text": "def doc_to_text_cot(doc) -> str:\n    \"\"\"\n    Answer the following question about the given passage. [Base your answer on the reasoning below.]\n    \n    Passage: <passage>\n    \n    Question: <question>\n    A. <choice1>\n    B. <choice2>\n    C. <choice3>\n    D. <choice4>\n    [E. <choice5>]\n    \n    [Reasoning: <reasoning>]\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. Base your answer on the reasoning below.\\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 += \"Reasoning: \" + doc[\"reasoning_trace\"] + \"\\n\\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
+      }
+    },
+    "repudiandae-autem-9860_logiqa_cot": {
+      "task": "repudiandae-autem-9860_logiqa_cot",
+      "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/repudiandae-autem-9860-logiqa.parquet"
+        }
+      },
+      "test_split": "test",
+      "doc_to_text": "def doc_to_text_cot(doc) -> str:\n    \"\"\"\n    Answer the following question about the given passage. [Base your answer on the reasoning below.]\n    \n    Passage: <passage>\n    \n    Question: <question>\n    A. <choice1>\n    B. <choice2>\n    C. <choice3>\n    D. <choice4>\n    [E. <choice5>]\n    \n    [Reasoning: <reasoning>]\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. Base your answer on the reasoning below.\\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 += \"Reasoning: \" + doc[\"reasoning_trace\"] + \"\\n\\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
+      }
+    },
+    "repudiandae-autem-9860_lsat-ar_cot": {
+      "task": "repudiandae-autem-9860_lsat-ar_cot",
+      "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/repudiandae-autem-9860-lsat-ar.parquet"
+        }
+      },
+      "test_split": "test",
+      "doc_to_text": "def doc_to_text_cot(doc) -> str:\n    \"\"\"\n    Answer the following question about the given passage. [Base your answer on the reasoning below.]\n    \n    Passage: <passage>\n    \n    Question: <question>\n    A. <choice1>\n    B. <choice2>\n    C. <choice3>\n    D. <choice4>\n    [E. <choice5>]\n    \n    [Reasoning: <reasoning>]\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. Base your answer on the reasoning below.\\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 += \"Reasoning: \" + doc[\"reasoning_trace\"] + \"\\n\\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
+      }
+    },
+    "repudiandae-autem-9860_lsat-lr_cot": {
+      "task": "repudiandae-autem-9860_lsat-lr_cot",
+      "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/repudiandae-autem-9860-lsat-lr.parquet"
+        }
+      },
+      "test_split": "test",
+      "doc_to_text": "def doc_to_text_cot(doc) -> str:\n    \"\"\"\n    Answer the following question about the given passage. [Base your answer on the reasoning below.]\n    \n    Passage: <passage>\n    \n    Question: <question>\n    A. <choice1>\n    B. <choice2>\n    C. <choice3>\n    D. <choice4>\n    [E. <choice5>]\n    \n    [Reasoning: <reasoning>]\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. Base your answer on the reasoning below.\\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 += \"Reasoning: \" + doc[\"reasoning_trace\"] + \"\\n\\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
+      }
+    },
+    "repudiandae-autem-9860_lsat-rc_cot": {
+      "task": "repudiandae-autem-9860_lsat-rc_cot",
+      "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/repudiandae-autem-9860-lsat-rc.parquet"
+        }
+      },
+      "test_split": "test",
+      "doc_to_text": "def doc_to_text_cot(doc) -> str:\n    \"\"\"\n    Answer the following question about the given passage. [Base your answer on the reasoning below.]\n    \n    Passage: <passage>\n    \n    Question: <question>\n    A. <choice1>\n    B. <choice2>\n    C. <choice3>\n    D. <choice4>\n    [E. <choice5>]\n    \n    [Reasoning: <reasoning>]\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. Base your answer on the reasoning below.\\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 += \"Reasoning: \" + doc[\"reasoning_trace\"] + \"\\n\\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": {
+    "repudiandae-autem-9860_logiqa2_cot": 0.0,
+    "repudiandae-autem-9860_logiqa_cot": 0.0,
+    "repudiandae-autem-9860_lsat-ar_cot": 0.0,
+    "repudiandae-autem-9860_lsat-lr_cot": 0.0,
+    "repudiandae-autem-9860_lsat-rc_cot": 0.0
+  },
+  "n-shot": {
+    "repudiandae-autem-9860_logiqa2_cot": 0,
+    "repudiandae-autem-9860_logiqa_cot": 0,
+    "repudiandae-autem-9860_lsat-ar_cot": 0,
+    "repudiandae-autem-9860_lsat-lr_cot": 0,
+    "repudiandae-autem-9860_lsat-rc_cot": 0
+  },
+  "higher_is_better": {
+    "repudiandae-autem-9860_logiqa2_cot": {
+      "acc": true
+    },
+    "repudiandae-autem-9860_logiqa_cot": {
+      "acc": true
+    },
+    "repudiandae-autem-9860_lsat-ar_cot": {
+      "acc": true
+    },
+    "repudiandae-autem-9860_lsat-lr_cot": {
+      "acc": true
+    },
+    "repudiandae-autem-9860_lsat-rc_cot": {
+      "acc": true
+    }
+  },
+  "n-samples": {
+    "repudiandae-autem-9860_lsat-rc_cot": {
+      "original": 269,
+      "effective": 269
+    },
+    "repudiandae-autem-9860_lsat-lr_cot": {
+      "original": 510,
+      "effective": 510
+    },
+    "repudiandae-autem-9860_lsat-ar_cot": {
+      "original": 230,
+      "effective": 230
+    },
+    "repudiandae-autem-9860_logiqa_cot": {
+      "original": 626,
+      "effective": 626
+    },
+    "repudiandae-autem-9860_logiqa2_cot": {
+      "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": 1725911244.8980067,
+  "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": 7718560.780495724,
+  "end_time": 7719776.927820672,
+  "total_evaluation_time_seconds": "1216.1473249485716"
+}