{ "results": { "gat": { "acc,none": 0.4142104603035244, "acc_stderr,none": 0.0038397567806533668, "alias": "gat" }, "gat_algebra": { "alias": " - gat_algebra", "acc,none": 0.3888682745825603, "acc_stderr,none": 0.009392255011265211 }, "gat_analogy": { "alias": " - gat_analogy", "acc,none": 0.3493624772313297, "acc_stderr,none": 0.009101555643753388 }, "gat_arithmetic": { "alias": " - gat_arithmetic", "acc,none": 0.36474052263525947, "acc_stderr,none": 0.009236399342894993 }, "gat_association": { "alias": " - gat_association", "acc,none": 0.5023923444976076, "acc_stderr,none": 0.0154744343816748 }, "gat_comparisons": { "alias": " - gat_comparisons", "acc,none": 0.30901639344262294, "acc_stderr,none": 0.013234964445015209 }, "gat_completion": { "alias": " - gat_completion", "acc,none": 0.5462809917355372, "acc_stderr,none": 0.01431819857472042 }, "gat_contextual": { "alias": " - gat_contextual", "acc,none": 0.32745398773006135, "acc_stderr,none": 0.013000616127135718 }, "gat_geometry": { "alias": " - gat_geometry", "acc,none": 0.43561643835616437, "acc_stderr,none": 0.025988942967463693 }, "gat_reading": { "alias": " - gat_reading", "acc,none": 0.5512287334593573, "acc_stderr,none": 0.00967270003130818 } }, "groups": { "gat": { "acc,none": 0.4142104603035244, "acc_stderr,none": 0.0038397567806533668, "alias": "gat" } }, "group_subtasks": { "gat": [ "gat_analogy", "gat_association", "gat_completion", "gat_reading", "gat_algebra", "gat_arithmetic", "gat_comparisons", "gat_contextual", "gat_geometry" ] }, "configs": { "gat_algebra": { "task": "gat_algebra", "dataset_path": "lm_eval/tasks/gat/gat_data/gat.py", "dataset_name": "algebra", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "validation", "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n", "doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:", "doc_to_target": "{{label}}", "doc_to_choice": [ "\u0623", "\u0628", "\u062c", "\u062f" ], "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 } }, "gat_analogy": { "task": "gat_analogy", "dataset_path": "lm_eval/tasks/gat/gat_data/gat.py", "dataset_name": "analogy", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "validation", "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n", "doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:", "doc_to_target": "{{label}}", "doc_to_choice": [ "\u0623", "\u0628", "\u062c", "\u062f" ], "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 } }, "gat_arithmetic": { "task": "gat_arithmetic", "dataset_path": "lm_eval/tasks/gat/gat_data/gat.py", "dataset_name": "arithmetic", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "validation", "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n", "doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:", "doc_to_target": "{{label}}", "doc_to_choice": [ "\u0623", "\u0628", "\u062c", "\u062f" ], "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 } }, "gat_association": { "task": "gat_association", "dataset_path": "lm_eval/tasks/gat/gat_data/gat.py", "dataset_name": "association", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "validation", "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n", "doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:", "doc_to_target": "{{label}}", "doc_to_choice": [ "\u0623", "\u0628", "\u062c", "\u062f" ], "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 } }, "gat_comparisons": { "task": "gat_comparisons", "dataset_path": "lm_eval/tasks/gat/gat_data/gat.py", "dataset_name": "comparisons", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "validation", "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n", "doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:", "doc_to_target": "{{label}}", "doc_to_choice": [ "\u0623", "\u0628", "\u062c", "\u062f" ], "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 } }, "gat_completion": { "task": "gat_completion", "dataset_path": "lm_eval/tasks/gat/gat_data/gat.py", "dataset_name": "completion", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "validation", "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n", "doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:", "doc_to_target": "{{label}}", "doc_to_choice": [ "\u0623", "\u0628", "\u062c", "\u062f" ], "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 } }, "gat_contextual": { "task": "gat_contextual", "dataset_path": "lm_eval/tasks/gat/gat_data/gat.py", "dataset_name": "contextual", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "validation", "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n", "doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:", "doc_to_target": "{{label}}", "doc_to_choice": [ "\u0623", "\u0628", "\u062c", "\u062f" ], "description": "\u0627\u0648\u062c\u062f \u0627\u0644\u062e\u0637\u0623 \u0627\u0644\u0633\u064a\u0627\u0642\u064a \u0641\u064a \u0627\u0644\u0639\u0628\u0627\u0631\u0629 \u0627\u0644\u062a\u0627\u0644\u064a\u0629 \u0645\u0646 \u0628\u064a\u0646 \u0627\u0644\u062e\u064a\u0627\u0631\u0627\u062a:", "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 } }, "gat_geometry": { "task": "gat_geometry", "dataset_path": "lm_eval/tasks/gat/gat_data/gat.py", "dataset_name": "geometry", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "validation", "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n", "doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:", "doc_to_target": "{{label}}", "doc_to_choice": [ "\u0623", "\u0628", "\u062c", "\u062f" ], "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 } }, "gat_reading": { "task": "gat_reading", "dataset_path": "lm_eval/tasks/gat/gat_data/gat.py", "dataset_name": "reading", "dataset_kwargs": { "trust_remote_code": true }, "test_split": "test", "fewshot_split": "validation", "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n # def _process_doc(doc):\n \n # subject = doc['id'].split(\"-\")[0]\n # subject_ar = subtasks_ar[subtasks.index(subject)]\n # out_doc = {**doc, 'subject_ar': subject_ar}\n # print(subject_ar)\n # print(out_doc)\n # return out_doc\n\n return dataset\n", "doc_to_text": "{{question}}\n\u0623. {{choices[0]}}\n\u0628. {{choices[1]}}\n\u062c. {{choices[2]}}\n\u062f. {{choices[3]}}\n\u0627\u0644\u0627\u062c\u0627\u0628\u0629:", "doc_to_target": "{{label}}", "doc_to_choice": [ "\u0623", "\u0628", "\u062c", "\u062f" ], "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": { "gat": 0, "gat_algebra": 0.0, "gat_analogy": 0.0, "gat_arithmetic": 0.0, "gat_association": 0.0, "gat_comparisons": 0.0, "gat_completion": 0.0, "gat_contextual": 0.0, "gat_geometry": 0.0, "gat_reading": 0.0 }, "n-shot": { "gat_algebra": 0, "gat_analogy": 0, "gat_arithmetic": 0, "gat_association": 0, "gat_comparisons": 0, "gat_completion": 0, "gat_contextual": 0, "gat_geometry": 0, "gat_reading": 0 }, "higher_is_better": { "gat": { "acc": true }, "gat_algebra": { "acc": true }, "gat_analogy": { "acc": true }, "gat_arithmetic": { "acc": true }, "gat_association": { "acc": true }, "gat_comparisons": { "acc": true }, "gat_completion": { "acc": true }, "gat_contextual": { "acc": true }, "gat_geometry": { "acc": true }, "gat_reading": { "acc": true } }, "n-samples": { "gat_analogy": { "original": 2745, "effective": 2745 }, "gat_association": { "original": 1045, "effective": 1045 }, "gat_completion": { "original": 1210, "effective": 1210 }, "gat_reading": { "original": 2645, "effective": 2645 }, "gat_algebra": { "original": 2695, "effective": 2695 }, "gat_arithmetic": { "original": 2717, "effective": 2717 }, "gat_comparisons": { "original": 1220, "effective": 1220 }, "gat_contextual": { "original": 1304, "effective": 1304 }, "gat_geometry": { "original": 365, "effective": 365 } }, "config": { "model": "hf", "model_args": "parallelize=False,pretrained=Qwen/Qwen2.5-7B-Instruct,trust_remote_code=True,mm=False", "model_num_parameters": 7615616512, "model_dtype": "torch.bfloat16", "model_revision": "main", "model_sha": "bb46c15ee4bb56c5b63245ef50fd7637234d6f75", "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": "3127d82f", "date": 1730951149.5236645, "pretty_env_info": "PyTorch version: 2.1.0a0+29c30b1\nIs debug build: False\nCUDA used to build PyTorch: 12.2\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==1.22.2\n[pip3] pytorch-lightning==2.0.7\n[pip3] pytorch-quantization==2.1.2\n[pip3] torch==2.1.0a0+29c30b1\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==0.16.0a0\n[pip3] triton==2.0.0.dev20221202\n[conda] Could not collect", "transformers_version": "4.38.2", "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": 32768, "task_hashes": {}, "model_source": "hf", "model_name": "Qwen/Qwen2.5-7B-Instruct", "model_name_sanitized": "Qwen__Qwen2.5-7B-Instruct", "system_instruction": null, "system_instruction_sha": null, "fewshot_as_multiturn": false, "chat_template": null, "chat_template_sha": null, "start_time": 8058.842983944, "end_time": 9035.124412401, "total_evaluation_time_seconds": "976.2814284570013" }