results_2024-11-30T09-11-17.191351.json

{
  "results": {
    "leaderboard_musr": {
      " ": " ",
      "alias": "leaderboard_musr"
    },
    "leaderboard_musr_murder_mysteries": {
      "alias": " - leaderboard_musr_murder_mysteries",
      "acc_norm,none": 0.54,
      "acc_norm_stderr,none": 0.03158465389149902
    },
    "leaderboard_musr_object_placements": {
      "alias": " - leaderboard_musr_object_placements",
      "acc_norm,none": 0.234375,
      "acc_norm_stderr,none": 0.02652733398834892
    },
    "leaderboard_musr_team_allocation": {
      "alias": " - leaderboard_musr_team_allocation",
      "acc_norm,none": 0.32,
      "acc_norm_stderr,none": 0.029561724955241033
    }
  },
  "group_subtasks": {
    "leaderboard_musr": [
      "leaderboard_musr_murder_mysteries",
      "leaderboard_musr_object_placements",
      "leaderboard_musr_team_allocation"
    ]
  },
  "configs": {
    "leaderboard_musr_murder_mysteries": {
      "task": "leaderboard_musr_murder_mysteries",
      "dataset_path": "TAUR-Lab/MuSR",
      "test_split": "murder_mysteries",
      "doc_to_text": "def doc_to_text(doc):\n    \"\"\"\n    Convert a doc to text.\n    \"\"\"\n    choices = \"\"\n    for i, choice in enumerate(ast.literal_eval(doc[\"choices\"])):\n        choices += f\"{i+1} - {choice}\\n\"\n\n    text = DOC_TO_TEXT.format(\n        narrative=doc[\"narrative\"], question=doc[\"question\"], choices=choices\n    )\n\n    return text\n",
      "doc_to_target": "{{answer_choice}}",
      "doc_to_choice": "{{choices}}",
      "description": "",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "acc_norm",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "multiple_choice",
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0
      }
    },
    "leaderboard_musr_object_placements": {
      "task": "leaderboard_musr_object_placements",
      "dataset_path": "TAUR-Lab/MuSR",
      "test_split": "object_placements",
      "doc_to_text": "def doc_to_text(doc):\n    \"\"\"\n    Convert a doc to text.\n    \"\"\"\n    choices = \"\"\n    for i, choice in enumerate(ast.literal_eval(doc[\"choices\"])):\n        choices += f\"{i+1} - {choice}\\n\"\n\n    text = DOC_TO_TEXT.format(\n        narrative=doc[\"narrative\"], question=doc[\"question\"], choices=choices\n    )\n\n    return text\n",
      "doc_to_target": "{{answer_choice}}",
      "doc_to_choice": "{{choices}}",
      "description": "",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "acc_norm",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "multiple_choice",
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0
      }
    },
    "leaderboard_musr_team_allocation": {
      "task": "leaderboard_musr_team_allocation",
      "dataset_path": "TAUR-Lab/MuSR",
      "test_split": "team_allocation",
      "doc_to_text": "def doc_to_text(doc):\n    \"\"\"\n    Convert a doc to text.\n    \"\"\"\n    choices = \"\"\n    for i, choice in enumerate(ast.literal_eval(doc[\"choices\"])):\n        choices += f\"{i+1} - {choice}\\n\"\n\n    text = DOC_TO_TEXT.format(\n        narrative=doc[\"narrative\"], question=doc[\"question\"], choices=choices\n    )\n\n    return text\n",
      "doc_to_target": "{{answer_choice}}",
      "doc_to_choice": "{{choices}}",
      "description": "",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "acc_norm",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "multiple_choice",
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0
      }
    }
  },
  "versions": {
    "leaderboard_musr_murder_mysteries": 1.0,
    "leaderboard_musr_object_placements": 1.0,
    "leaderboard_musr_team_allocation": 1.0
  },
  "n-shot": {
    "leaderboard_musr_murder_mysteries": 0,
    "leaderboard_musr_object_placements": 0,
    "leaderboard_musr_team_allocation": 0
  },
  "higher_is_better": {
    "leaderboard_musr": {
      "acc_norm": true
    },
    "leaderboard_musr_murder_mysteries": {
      "acc_norm": true
    },
    "leaderboard_musr_object_placements": {
      "acc_norm": true
    },
    "leaderboard_musr_team_allocation": {
      "acc_norm": true
    }
  },
  "n-samples": {
    "leaderboard_musr_murder_mysteries": {
      "original": 250,
      "effective": 250
    },
    "leaderboard_musr_object_placements": {
      "original": 256,
      "effective": 256
    },
    "leaderboard_musr_team_allocation": {
      "original": 250,
      "effective": 250
    }
  },
  "config": {
    "model": "hf",
    "model_args": "pretrained=DevQuasar/analytical_reasoning_r16a32_unsloth-Llama-3.2-3B-Instruct-bnb-4bit",
    "batch_size": "auto:4",
    "batch_sizes": [
      16,
      16,
      16,
      32
    ],
    "device": null,
    "use_cache": "eval_cache",
    "limit": null,
    "bootstrap_iters": 100000,
    "gen_kwargs": null,
    "random_seed": 0,
    "numpy_seed": 1234,
    "torch_seed": 1234,
    "fewshot_seed": 1234
  },
  "git_hash": "0230356",
  "date": 1732986471.4917576,
  "pretty_env_info": "PyTorch version: 2.5.1+cu124\nIs debug build: False\nCUDA used to build PyTorch: 12.4\nROCM used to build PyTorch: N/A\n\nOS: Debian GNU/Linux 12 (bookworm) (x86_64)\nGCC version: (Debian 12.2.0-14) 12.2.0\nClang version: Could not collect\nCMake version: Could not collect\nLibc version: glibc-2.36\n\nPython version: 3.11.10 (main, Oct  3 2024, 07:29:13) [GCC 11.2.0] (64-bit runtime)\nPython platform: Linux-6.1.0-26-amd64-x86_64-with-glibc2.36\nIs CUDA available: True\nCUDA runtime version: Could not collect\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA GeForce GTX 1050 Ti\nGPU 1: Tesla P40\nGPU 2: Tesla V100-PCIE-32GB\nGPU 3: Tesla V100-PCIE-32GB\n\nNvidia driver version: 535.183.01\ncuDNN version: Could not collect\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):                               32\nOn-line CPU(s) list:                  0-31\nVendor ID:                            AuthenticAMD\nModel name:                           AMD Ryzen Threadripper 1950X 16-Core Processor\nCPU family:                           23\nModel:                                1\nThread(s) per core:                   2\nCore(s) per socket:                   16\nSocket(s):                            1\nStepping:                             1\nFrequency boost:                      enabled\nCPU(s) scaling MHz:                   66%\nCPU max MHz:                          3400.0000\nCPU min MHz:                          2200.0000\nBogoMIPS:                             6786.43\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 amd_dcm aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb hw_pstate ssbd ibpb vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt sha_ni xsaveopt xsavec xgetbv1 clzero irperf xsaveerptr arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif overflow_recov succor smca sev\nVirtualization:                       AMD-V\nL1d cache:                            512 KiB (16 instances)\nL1i cache:                            1 MiB (16 instances)\nL2 cache:                             8 MiB (16 instances)\nL3 cache:                             32 MiB (4 instances)\nNUMA node(s):                         1\nNUMA node0 CPU(s):                    0-31\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 Reg file data sampling: Not affected\nVulnerability Retbleed:               Mitigation; untrained return thunk; SMT vulnerable\nVulnerability Spec rstack overflow:   Mitigation; safe RET\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 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==2.1.3\n[pip3] torch==2.5.1\n[pip3] triton==3.1.0\n[conda] numpy                     2.1.3                    pypi_0    pypi\n[conda] torch                     2.5.1                    pypi_0    pypi\n[conda] triton                    3.1.0                    pypi_0    pypi",
  "transformers_version": "4.46.3",
  "upper_git_hash": null,
  "tokenizer_pad_token": [
    "<|finetune_right_pad_id|>",
    "128004"
  ],
  "tokenizer_eos_token": [
    "<|eot_id|>",
    "128009"
  ],
  "tokenizer_bos_token": [
    "<|begin_of_text|>",
    "128000"
  ],
  "eot_token_id": 128009,
  "max_length": 131072,
  "task_hashes": {
    "leaderboard_musr_murder_mysteries": "a696259562ea5c5c09a2613e30526fae1de29f55da9e28e8d7e8a53027e6d330",
    "leaderboard_musr_object_placements": "3aa8c5e5bc59cd6ba2326269b9f0bf3cee8cba1b4e9e1d1330cf5f1f59ea0dce",
    "leaderboard_musr_team_allocation": "5a75f135c145ee861a1cf31b63346709ef41b9d542be6a61c5818c210a3797a5"
  },
  "model_source": "hf",
  "model_name": "DevQuasar/analytical_reasoning_r16a32_unsloth-Llama-3.2-3B-Instruct-bnb-4bit",
  "model_name_sanitized": "DevQuasar__analytical_reasoning_r16a32_unsloth-Llama-3.2-3B-Instruct-bnb-4bit",
  "system_instruction": null,
  "system_instruction_sha": null,
  "fewshot_as_multiturn": false,
  "chat_template": null,
  "chat_template_sha": null,
  "start_time": 52195.45405349,
  "end_time": 52407.302247922,
  "total_evaluation_time_seconds": "211.84819443200104"
}