{ "results": { "minerva_math": { "exact_match,none": 0.1344, "exact_match_stderr,none": 0.00469690840313393, "alias": "minerva_math" }, "minerva_math_algebra": { "alias": " - minerva_math_algebra", "exact_match,none": 0.1954507160909857, "exact_match_stderr,none": 0.011514699662714494 }, "minerva_math_counting_and_prob": { "alias": " - minerva_math_counting_and_prob", "exact_match,none": 0.12236286919831224, "exact_match_stderr,none": 0.015067866025208529 }, "minerva_math_geometry": { "alias": " - minerva_math_geometry", "exact_match,none": 0.09603340292275574, "exact_match_stderr,none": 0.013476384772608527 }, "minerva_math_intermediate_algebra": { "alias": " - minerva_math_intermediate_algebra", "exact_match,none": 0.04540420819490587, "exact_match_stderr,none": 0.006931935965006335 }, "minerva_math_num_theory": { "alias": " - minerva_math_num_theory", "exact_match,none": 0.08148148148148149, "exact_match_stderr,none": 0.011783628281121686 }, "minerva_math_prealgebra": { "alias": " - minerva_math_prealgebra", "exact_match,none": 0.2571756601607348, "exact_match_stderr,none": 0.014818299496867965 }, "minerva_math_precalc": { "alias": " - minerva_math_precalc", "exact_match,none": 0.04945054945054945, "exact_match_stderr,none": 0.009286983354895582 } }, "groups": { "minerva_math": { "exact_match,none": 0.1344, "exact_match_stderr,none": 0.00469690840313393, "alias": "minerva_math" } }, "group_subtasks": { "minerva_math": [ "minerva_math_algebra", "minerva_math_counting_and_prob", "minerva_math_geometry", "minerva_math_intermediate_algebra", "minerva_math_num_theory", "minerva_math_prealgebra", "minerva_math_precalc" ] }, "configs": { "minerva_math_algebra": { "task": "minerva_math_algebra", "tag": [ "math_word_problems" ], "group": [ "math_word_problems" ], "dataset_path": "EleutherAI/hendrycks_math", "dataset_name": "algebra", "dataset_kwargs": { "trust_remote_code": true }, "training_split": "train", "test_split": "test", "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc: dict) -> dict:\n out_doc = {\n \"problem\": doc[\"problem\"],\n \"solution\": doc[\"solution\"],\n \"answer\": normalize_final_answer(\n remove_boxed(last_boxed_only_string(doc[\"solution\"]))\n ),\n }\n if getattr(doc, \"few_shot\", None) is not None:\n out_doc[\"few_shot\"] = True\n return out_doc\n\n return dataset.map(_process_doc)\n", "doc_to_text": "def doc_to_text(doc: dict) -> str:\n return \"Problem:\" + \"\\n\" + doc[\"problem\"] + \"\\n\\n\" + \"Solution:\"\n", "doc_to_target": "{{answer if few_shot is undefined else solution}}", "process_results": "def process_results(doc: dict, results: List[str]) -> Dict[str, int]:\n candidates = results[0]\n\n unnormalized_answer = get_unnormalized_answer(candidates)\n answer = normalize_final_answer(unnormalized_answer)\n\n if is_equiv(answer, doc[\"answer\"]):\n retval = 1\n else:\n retval = 0\n\n results = {\n \"exact_match\": retval,\n }\n return results\n", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "samples": "" }, "num_fewshot": 4, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true } ], "output_type": "generate_until", "generation_kwargs": { "until": [ "Problem:" ], "do_sample": false, "temperature": 0.0 }, "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "minerva_math_counting_and_prob": { "task": "minerva_math_counting_and_prob", "tag": [ "math_word_problems" ], "group": [ "math_word_problems" ], "dataset_path": "EleutherAI/hendrycks_math", "dataset_name": "counting_and_probability", "dataset_kwargs": { "trust_remote_code": true }, "training_split": "train", "test_split": "test", "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc: dict) -> dict:\n out_doc = {\n \"problem\": doc[\"problem\"],\n \"solution\": doc[\"solution\"],\n \"answer\": normalize_final_answer(\n remove_boxed(last_boxed_only_string(doc[\"solution\"]))\n ),\n }\n if getattr(doc, \"few_shot\", None) is not None:\n out_doc[\"few_shot\"] = True\n return out_doc\n\n return dataset.map(_process_doc)\n", "doc_to_text": "def doc_to_text(doc: dict) -> str:\n return \"Problem:\" + \"\\n\" + doc[\"problem\"] + \"\\n\\n\" + \"Solution:\"\n", "doc_to_target": "{{answer if few_shot is undefined else solution}}", "process_results": "def process_results(doc: dict, results: List[str]) -> Dict[str, int]:\n candidates = results[0]\n\n unnormalized_answer = get_unnormalized_answer(candidates)\n answer = normalize_final_answer(unnormalized_answer)\n\n if is_equiv(answer, doc[\"answer\"]):\n retval = 1\n else:\n retval = 0\n\n results = {\n \"exact_match\": retval,\n }\n return results\n", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "samples": "" }, "num_fewshot": 4, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true } ], "output_type": "generate_until", "generation_kwargs": { "until": [ "Problem:" ], "do_sample": false, "temperature": 0.0 }, "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "minerva_math_geometry": { "task": "minerva_math_geometry", "tag": [ "math_word_problems" ], "group": [ "math_word_problems" ], "dataset_path": "EleutherAI/hendrycks_math", "dataset_name": "geometry", "dataset_kwargs": { "trust_remote_code": true }, "training_split": "train", "test_split": "test", "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc: dict) -> dict:\n out_doc = {\n \"problem\": doc[\"problem\"],\n \"solution\": doc[\"solution\"],\n \"answer\": normalize_final_answer(\n remove_boxed(last_boxed_only_string(doc[\"solution\"]))\n ),\n }\n if getattr(doc, \"few_shot\", None) is not None:\n out_doc[\"few_shot\"] = True\n return out_doc\n\n return dataset.map(_process_doc)\n", "doc_to_text": "def doc_to_text(doc: dict) -> str:\n return \"Problem:\" + \"\\n\" + doc[\"problem\"] + \"\\n\\n\" + \"Solution:\"\n", "doc_to_target": "{{answer if few_shot is undefined else solution}}", "process_results": "def process_results(doc: dict, results: List[str]) -> Dict[str, int]:\n candidates = results[0]\n\n unnormalized_answer = get_unnormalized_answer(candidates)\n answer = normalize_final_answer(unnormalized_answer)\n\n if is_equiv(answer, doc[\"answer\"]):\n retval = 1\n else:\n retval = 0\n\n results = {\n \"exact_match\": retval,\n }\n return results\n", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "samples": "" }, "num_fewshot": 4, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true } ], "output_type": "generate_until", "generation_kwargs": { "until": [ "Problem:" ], "do_sample": false, "temperature": 0.0 }, "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "minerva_math_intermediate_algebra": { "task": "minerva_math_intermediate_algebra", "tag": [ "math_word_problems" ], "group": [ "math_word_problems" ], "dataset_path": "EleutherAI/hendrycks_math", "dataset_name": "intermediate_algebra", "dataset_kwargs": { "trust_remote_code": true }, "training_split": "train", "test_split": "test", "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc: dict) -> dict:\n out_doc = {\n \"problem\": doc[\"problem\"],\n \"solution\": doc[\"solution\"],\n \"answer\": normalize_final_answer(\n remove_boxed(last_boxed_only_string(doc[\"solution\"]))\n ),\n }\n if getattr(doc, \"few_shot\", None) is not None:\n out_doc[\"few_shot\"] = True\n return out_doc\n\n return dataset.map(_process_doc)\n", "doc_to_text": "def doc_to_text(doc: dict) -> str:\n return \"Problem:\" + \"\\n\" + doc[\"problem\"] + \"\\n\\n\" + \"Solution:\"\n", "doc_to_target": "{{answer if few_shot is undefined else solution}}", "process_results": "def process_results(doc: dict, results: List[str]) -> Dict[str, int]:\n candidates = results[0]\n\n unnormalized_answer = get_unnormalized_answer(candidates)\n answer = normalize_final_answer(unnormalized_answer)\n\n if is_equiv(answer, doc[\"answer\"]):\n retval = 1\n else:\n retval = 0\n\n results = {\n \"exact_match\": retval,\n }\n return results\n", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "samples": "" }, "num_fewshot": 4, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true } ], "output_type": "generate_until", "generation_kwargs": { "until": [ "Problem:" ], "do_sample": false, "temperature": 0.0 }, "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "minerva_math_num_theory": { "task": "minerva_math_num_theory", "tag": [ "math_word_problems" ], "group": [ "math_word_problems" ], "dataset_path": "EleutherAI/hendrycks_math", "dataset_name": "number_theory", "dataset_kwargs": { "trust_remote_code": true }, "training_split": "train", "test_split": "test", "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc: dict) -> dict:\n out_doc = {\n \"problem\": doc[\"problem\"],\n \"solution\": doc[\"solution\"],\n \"answer\": normalize_final_answer(\n remove_boxed(last_boxed_only_string(doc[\"solution\"]))\n ),\n }\n if getattr(doc, \"few_shot\", None) is not None:\n out_doc[\"few_shot\"] = True\n return out_doc\n\n return dataset.map(_process_doc)\n", "doc_to_text": "def doc_to_text(doc: dict) -> str:\n return \"Problem:\" + \"\\n\" + doc[\"problem\"] + \"\\n\\n\" + \"Solution:\"\n", "doc_to_target": "{{answer if few_shot is undefined else solution}}", "process_results": "def process_results(doc: dict, results: List[str]) -> Dict[str, int]:\n candidates = results[0]\n\n unnormalized_answer = get_unnormalized_answer(candidates)\n answer = normalize_final_answer(unnormalized_answer)\n\n if is_equiv(answer, doc[\"answer\"]):\n retval = 1\n else:\n retval = 0\n\n results = {\n \"exact_match\": retval,\n }\n return results\n", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "samples": "" }, "num_fewshot": 4, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true } ], "output_type": "generate_until", "generation_kwargs": { "until": [ "Problem:" ], "do_sample": false, "temperature": 0.0 }, "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "minerva_math_prealgebra": { "task": "minerva_math_prealgebra", "tag": [ "math_word_problems" ], "group": [ "math_word_problems" ], "dataset_path": "EleutherAI/hendrycks_math", "dataset_name": "prealgebra", "dataset_kwargs": { "trust_remote_code": true }, "training_split": "train", "test_split": "test", "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc: dict) -> dict:\n out_doc = {\n \"problem\": doc[\"problem\"],\n \"solution\": doc[\"solution\"],\n \"answer\": normalize_final_answer(\n remove_boxed(last_boxed_only_string(doc[\"solution\"]))\n ),\n }\n if getattr(doc, \"few_shot\", None) is not None:\n out_doc[\"few_shot\"] = True\n return out_doc\n\n return dataset.map(_process_doc)\n", "doc_to_text": "def doc_to_text(doc: dict) -> str:\n return \"Problem:\" + \"\\n\" + doc[\"problem\"] + \"\\n\\n\" + \"Solution:\"\n", "doc_to_target": "{{answer if few_shot is undefined else solution}}", "process_results": "def process_results(doc: dict, results: List[str]) -> Dict[str, int]:\n candidates = results[0]\n\n unnormalized_answer = get_unnormalized_answer(candidates)\n answer = normalize_final_answer(unnormalized_answer)\n\n if is_equiv(answer, doc[\"answer\"]):\n retval = 1\n else:\n retval = 0\n\n results = {\n \"exact_match\": retval,\n }\n return results\n", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "samples": "" }, "num_fewshot": 4, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true } ], "output_type": "generate_until", "generation_kwargs": { "until": [ "Problem:" ], "do_sample": false, "temperature": 0.0 }, "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } }, "minerva_math_precalc": { "task": "minerva_math_precalc", "tag": [ "math_word_problems" ], "group": [ "math_word_problems" ], "dataset_path": "EleutherAI/hendrycks_math", "dataset_name": "precalculus", "dataset_kwargs": { "trust_remote_code": true }, "training_split": "train", "test_split": "test", "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n def _process_doc(doc: dict) -> dict:\n out_doc = {\n \"problem\": doc[\"problem\"],\n \"solution\": doc[\"solution\"],\n \"answer\": normalize_final_answer(\n remove_boxed(last_boxed_only_string(doc[\"solution\"]))\n ),\n }\n if getattr(doc, \"few_shot\", None) is not None:\n out_doc[\"few_shot\"] = True\n return out_doc\n\n return dataset.map(_process_doc)\n", "doc_to_text": "def doc_to_text(doc: dict) -> str:\n return \"Problem:\" + \"\\n\" + doc[\"problem\"] + \"\\n\\n\" + \"Solution:\"\n", "doc_to_target": "{{answer if few_shot is undefined else solution}}", "process_results": "def process_results(doc: dict, results: List[str]) -> Dict[str, int]:\n candidates = results[0]\n\n unnormalized_answer = get_unnormalized_answer(candidates)\n answer = normalize_final_answer(unnormalized_answer)\n\n if is_equiv(answer, doc[\"answer\"]):\n retval = 1\n else:\n retval = 0\n\n results = {\n \"exact_match\": retval,\n }\n return results\n", "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "first_n", "samples": "" }, "num_fewshot": 4, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true } ], "output_type": "generate_until", "generation_kwargs": { "until": [ "Problem:" ], "do_sample": false, "temperature": 0.0 }, "repeats": 1, "should_decontaminate": false, "metadata": { "version": 1.0 } } }, "versions": { "minerva_math": 1.0, "minerva_math_algebra": 1.0, "minerva_math_counting_and_prob": 1.0, "minerva_math_geometry": 1.0, "minerva_math_intermediate_algebra": 1.0, "minerva_math_num_theory": 1.0, "minerva_math_prealgebra": 1.0, "minerva_math_precalc": 1.0 }, "n-shot": { "minerva_math_algebra": 4, "minerva_math_counting_and_prob": 4, "minerva_math_geometry": 4, "minerva_math_intermediate_algebra": 4, "minerva_math_num_theory": 4, "minerva_math_prealgebra": 4, "minerva_math_precalc": 4 }, "higher_is_better": { "minerva_math": { "exact_match": true }, "minerva_math_algebra": { "exact_match": true }, "minerva_math_counting_and_prob": { "exact_match": true }, "minerva_math_geometry": { "exact_match": true }, "minerva_math_intermediate_algebra": { "exact_match": true }, "minerva_math_num_theory": { "exact_match": true }, "minerva_math_prealgebra": { "exact_match": true }, "minerva_math_precalc": { "exact_match": true } }, "n-samples": { "minerva_math_algebra": { "original": 1187, "effective": 1187 }, "minerva_math_counting_and_prob": { "original": 474, "effective": 474 }, "minerva_math_geometry": { "original": 479, "effective": 479 }, "minerva_math_intermediate_algebra": { "original": 903, "effective": 903 }, "minerva_math_num_theory": { "original": 540, "effective": 540 }, "minerva_math_prealgebra": { "original": 871, "effective": 871 }, "minerva_math_precalc": { "original": 546, "effective": 546 } }, "config": { "model": "hf", "model_args": "parallelize=True,pretrained=mistralai/Mistral-7B-Instruct-v0.3,trust_remote_code=True,mm=False,trust_remote_code=True", "model_num_parameters": 7248023552, "model_dtype": "torch.bfloat16", "model_revision": "main", "model_sha": "e0bc86c23ce5aae1db576c8cca6f06f1f73af2db", "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": 1732457421.434201, "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: 4890.89\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": "4.46.3", "upper_git_hash": null, "tokenizer_pad_token": [ "", "0" ], "tokenizer_eos_token": [ "", "2" ], "tokenizer_bos_token": [ "", "1" ], "eot_token_id": 2, "max_length": 32768, "task_hashes": {}, "model_source": "hf", "model_name": "mistralai/Mistral-7B-Instruct-v0.3", "model_name_sanitized": "mistralai__Mistral-7B-Instruct-v0.3", "system_instruction": null, "system_instruction_sha": null, "fewshot_as_multiturn": false, "chat_template": null, "chat_template_sha": null, "start_time": 937481.096308053, "end_time": 984028.729417881, "total_evaluation_time_seconds": "46547.63310982799" }