{
  "results": {
    "gsm8k": {
      "alias": "gsm8k",
      "exact_match,strict-match": 0.9325246398786959,
      "exact_match_stderr,strict-match": 0.006909475136357507,
      "exact_match,flexible-extract": 0.9014404852160728,
      "exact_match_stderr,flexible-extract": 0.008210320350946319
    }
  },
  "group_subtasks": {
    "gsm8k": []
  },
  "configs": {
    "gsm8k": {
      "task": "gsm8k",
      "tag": [
        "math_word_problems"
      ],
      "dataset_path": "gsm8k",
      "dataset_name": "main",
      "training_split": "train",
      "test_split": "test",
      "fewshot_split": "train",
      "doc_to_text": "Question: {{question}}\nAnswer:",
      "doc_to_target": "{{answer}}",
      "description": "",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 5,
      "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:",
          "</s>",
          "<|im_end|>"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "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": 5
  },
  "higher_is_better": {
    "gsm8k": {
      "exact_match": true
    }
  },
  "n-samples": {
    "gsm8k": {
      "original": 1319,
      "effective": 1319
    }
  },
  "config": {
    "model": "vllm",
    "model_args": "pretrained=Qwen/Qwen2.5-72B-Instruct,tensor_parallel_size=4,data_parallel_size=2,gpu_memory_utilization=0.9,download_dir=/tmp,enforce_eager=True",
    "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": "150ae04f",
  "date": 1737584197.045788,
  "pretty_env_info": "PyTorch version: 2.4.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\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==1.26.4\n[pip3] onnx==1.14.0\n[pip3] pytorch-lightning==2.0.7\n[pip3] pytorch-quantization==2.1.2\n[pip3] torch==2.4.0\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==0.19.0\n[pip3] triton==3.0.0\n[conda] Could not collect",
  "transformers_version": "4.48.1",
  "upper_git_hash": "086919bd66f4e15fdcd4b792a7b27a698c1ba091",
  "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": "vllm",
  "model_name": "Qwen/Qwen2.5-72B-Instruct",
  "model_name_sanitized": "Qwen__Qwen2.5-72B-Instruct",
  "system_instruction": null,
  "system_instruction_sha": null,
  "fewshot_as_multiturn": false,
  "chat_template": null,
  "chat_template_sha": null,
  "start_time": 126217.606737687,
  "end_time": 126466.075864702,
  "total_evaluation_time_seconds": "248.4691270149924"
}