{ "results": { "gsm8k": { "alias": "gsm8k", "exact_match,strict-match": 0.8521607278241091, "exact_match_stderr,strict-match": 0.00977682767914391, "exact_match,flexible-extract": 0.8529188779378317, "exact_match_stderr,flexible-extract": 0.009756063660359896 } }, "group_subtasks": { "gsm8k": [] }, "configs": { "gsm8k": { "task": "gsm8k", "tag": [ "math_word_problems" ], "dataset_path": "openai/gsm8k", "dataset_name": "main", "training_split": "train", "test_split": "test", "fewshot_split": "train", "doc_to_text": "Question: {{question}}\nAnswer:", "doc_to_target": "{{answer}}", "unsafe_code": false, "description": "", "target_delimiter": " ", "fewshot_delimiter": "\n\n", "fewshot_config": { "sampler": "default", "split": "train", "process_docs": null, "fewshot_indices": null, "samples": null, "doc_to_text": "Question: {{question}}\nAnswer:", "doc_to_choice": null, "doc_to_target": "{{answer}}", "gen_prefix": null, "fewshot_delimiter": "\n\n", "target_delimiter": " " }, "num_fewshot": 8, "metric_list": [ { "metric": "exact_match", "aggregation": "mean", "higher_is_better": true, "ignore_case": true, "ignore_punctuation": false, "regexes_to_ignore": [ ",", "\\$", "(?s).*#### ", "\\.$" ] } ], "output_type": "generate_until", "generation_kwargs": { "until": [ "Question:", "", "<|im_end|>" ], "do_sample": false, "temperature": 0.6, "max_gen_toks": 131072, "max_tokens": 131072, "top_p": 0.95, "top_k": 20, "min_p": 0, "repeat_penalty": 1.0, "presence_penalty": 1.0, "num_ctx": 262144 }, "repeats": 1, "filter_list": [ { "name": "strict-match", "filter": [ { "function": "regex", "regex_pattern": "#### (\\-?[0-9\\.\\,]+)" }, { "function": "take_first" } ] }, { "name": "flexible-extract", "filter": [ { "function": "regex", "group_select": -1, "regex_pattern": "(-?[$0-9.,]{2,})|(-?[0-9]+)" }, { "function": "take_first" } ] } ], "should_decontaminate": false, "metadata": { "version": 3.0 } } }, "versions": { "gsm8k": 3.0 }, "n-shot": { "gsm8k": 8 }, "higher_is_better": { "gsm8k": { "exact_match": true } }, "n-samples": { "gsm8k": { "original": 1319, "effective": 1319 } }, "config": { "model": "LocalChatCompletion", "model_args": null, "batch_size": 1, "batch_sizes": [], "device": null, "use_cache": null, "limit": null, "bootstrap_iters": 100000, "gen_kwargs": { "max_gen_toks": 131072, "max_tokens": 131072, "temperature": 0.6, "top_p": 0.95, "top_k": 20, "min_p": 0, "repeat_penalty": 1.0, "presence_penalty": 1.0, "num_ctx": 262144 }, "random_seed": 0, "numpy_seed": 1234, "torch_seed": 1234, "fewshot_seed": 1234 }, "git_hash": null, "date": 1778390867.1640942, "pretty_env_info": "PyTorch version: 2.6.0+cpu\nIs debug build: False\nCUDA used to build PyTorch: Could not collect\nROCM used to build PyTorch: N/A\n\nOS: Debian GNU/Linux 12 (bookworm) (x86_64)\nGCC version: (Debian 12.2.0-14+deb12u1) 12.2.0\nClang version: Could not collect\nCMake version: version 3.25.1\nLibc version: glibc-2.36\n\nPython version: 3.11.5 (main, Aug 26 2023, 07:22:50) [Clang 16.0.3 ] (64-bit runtime)\nPython platform: Linux-4.4.0-x86_64-with-glibc2.36\nIs CUDA available: False\nCUDA runtime version: 12.8.93\nCUDA_MODULE_LOADING set to: N/A\nGPU models and configuration: GPU 0: NVIDIA B200\nNvidia driver version: 580.95.05\ncuDNN version: Probably one of the following:\n/usr/lib/x86_64-linux-gnu/libcudnn.so.9.22.0\n/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.22.0\n/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.22.0\n/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.22.0\n/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.22.0\n/usr/lib/x86_64-linux-gnu/libcudnn_engines_tensor_ir.so.9.22.0\n/usr/lib/x86_64-linux-gnu/libcudnn_ext.so.9.22.0\n/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.22.0\n/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.22.0\n/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.22.0\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: 46 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 17\nOn-line CPU(s) list: 0-16\nVendor ID: AuthenticAMD\nModel name: unknown\nCPU family: 191\nModel: 2\nThread(s) per core: 1\nCore(s) per socket: 17\nSocket(s): 1\nStepping: unknown\nBogoMIPS: 5035.66\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 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 fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid movdiri movdir64b fsrm avx512_vp2intersect flush_l1d\nVirtualization: AMD-V\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] torch==2.6.0+cpu\n[conda] Could not collect", "transformers_version": "5.5.1", "lm_eval_version": "0.4.11", "upper_git_hash": null }