Upload 3 files

Evals/Tess-v2.5-Qwen2-72B-agieval_nous.json

@@ -0,0 +1,506 @@
+{
+  "results": {
+    "agieval_nous": {
+      "acc_norm,none": 0.5357423409269442,
+      "acc_norm_stderr,none": 0.00952110343229611,
+      "acc,none": 0.6233307148468186,
+      "acc_stderr,none": 0.009151821236525831,
+      "alias": "agieval_nous"
+    },
+    "agieval_aqua_rat": {
+      "acc,none": 0.5511811023622047,
+      "acc_stderr,none": 0.03126961011656295,
+      "acc_norm,none": 0.5118110236220472,
+      "acc_norm_stderr,none": 0.031425959141896394,
+      "alias": " - agieval_aqua_rat"
+    },
+    "agieval_logiqa_en": {
+      "acc,none": 0.554531490015361,
+      "acc_stderr,none": 0.019494627133439985,
+      "acc_norm,none": 0.46236559139784944,
+      "acc_norm_stderr,none": 0.019555980839597826,
+      "alias": " - agieval_logiqa_en"
+    },
+    "agieval_lsat_ar": {
+      "acc,none": 0.26956521739130435,
+      "acc_stderr,none": 0.02932276422894952,
+      "acc_norm,none": 0.2565217391304348,
+      "acc_norm_stderr,none": 0.028858814315305643,
+      "alias": " - agieval_lsat_ar"
+    },
+    "agieval_lsat_lr": {
+      "acc,none": 0.7,
+      "acc_stderr,none": 0.020311909655921973,
+      "acc_norm,none": 0.5764705882352941,
+      "acc_norm_stderr,none": 0.021901379648792133,
+      "alias": " - agieval_lsat_lr"
+    },
+    "agieval_lsat_rc": {
+      "acc,none": 0.7881040892193308,
+      "acc_stderr,none": 0.02496236224822418,
+      "acc_norm,none": 0.6765799256505576,
+      "acc_norm_stderr,none": 0.028574302844503813,
+      "alias": " - agieval_lsat_rc"
+    },
+    "agieval_sat_en": {
+      "acc,none": 0.8689320388349514,
+      "acc_stderr,none": 0.02357025313368066,
+      "acc_norm,none": 0.8446601941747572,
+      "acc_norm_stderr,none": 0.02529912276040303,
+      "alias": " - agieval_sat_en"
+    },
+    "agieval_sat_en_without_passage": {
+      "acc,none": 0.616504854368932,
+      "acc_stderr,none": 0.033960279445866416,
+      "acc_norm,none": 0.5194174757281553,
+      "acc_norm_stderr,none": 0.03489517135066013,
+      "alias": " - agieval_sat_en_without_passage"
+    },
+    "agieval_sat_math": {
+      "acc,none": 0.6772727272727272,
+      "acc_stderr,none": 0.03159203270502094,
+      "acc_norm,none": 0.5318181818181819,
+      "acc_norm_stderr,none": 0.03371838809107287,
+      "alias": " - agieval_sat_math"
+    }
+  },
+  "groups": {
+    "agieval_nous": {
+      "acc_norm,none": 0.5357423409269442,
+      "acc_norm_stderr,none": 0.00952110343229611,
+      "acc,none": 0.6233307148468186,
+      "acc_stderr,none": 0.009151821236525831,
+      "alias": "agieval_nous"
+    }
+  },
+  "group_subtasks": {
+    "agieval_nous": [
+      "agieval_sat_en",
+      "agieval_lsat_ar",
+      "agieval_sat_en_without_passage",
+      "agieval_aqua_rat",
+      "agieval_logiqa_en",
+      "agieval_sat_math",
+      "agieval_lsat_rc",
+      "agieval_lsat_lr"
+    ]
+  },
+  "configs": {
+    "agieval_aqua_rat": {
+      "task": "agieval_aqua_rat",
+      "group": [
+        "agieval",
+        "agieval_en",
+        "agieval_nous"
+      ],
+      "dataset_path": "hails/agieval-aqua-rat",
+      "test_split": "test",
+      "doc_to_text": "{{query}}",
+      "doc_to_target": "{{gold}}",
+      "doc_to_choice": "{{choices}}",
+      "process_results": "def process_results_mcqa(doc, results):\n    results = [result[0] for result in results]\n\n    gold = doc[\"gold\"]\n\n    acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n    completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n    acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n    return {\n        \"acc\": acc,\n        \"acc_norm\": acc_norm,\n    }\n",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "agieval_logiqa_en": {
+      "task": "agieval_logiqa_en",
+      "group": [
+        "agieval",
+        "agieval_nous",
+        "agieval_en"
+      ],
+      "dataset_path": "hails/agieval-logiqa-en",
+      "test_split": "test",
+      "doc_to_text": "{{query}}",
+      "doc_to_target": "{{gold}}",
+      "doc_to_choice": "{{choices}}",
+      "process_results": "def process_results_mcqa(doc, results):\n    results = [result[0] for result in results]\n\n    gold = doc[\"gold\"]\n\n    acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n    completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n    acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n    return {\n        \"acc\": acc,\n        \"acc_norm\": acc_norm,\n    }\n",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "agieval_lsat_ar": {
+      "task": "agieval_lsat_ar",
+      "group": [
+        "agieval",
+        "agieval_nous",
+        "agieval_en"
+      ],
+      "dataset_path": "hails/agieval-lsat-ar",
+      "test_split": "test",
+      "doc_to_text": "{{query}}",
+      "doc_to_target": "{{gold}}",
+      "doc_to_choice": "{{choices}}",
+      "process_results": "def process_results_mcqa(doc, results):\n    results = [result[0] for result in results]\n\n    gold = doc[\"gold\"]\n\n    acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n    completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n    acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n    return {\n        \"acc\": acc,\n        \"acc_norm\": acc_norm,\n    }\n",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "agieval_lsat_lr": {
+      "task": "agieval_lsat_lr",
+      "group": [
+        "agieval",
+        "agieval_nous",
+        "agieval_en"
+      ],
+      "dataset_path": "hails/agieval-lsat-lr",
+      "test_split": "test",
+      "doc_to_text": "{{query}}",
+      "doc_to_target": "{{gold}}",
+      "doc_to_choice": "{{choices}}",
+      "process_results": "def process_results_mcqa(doc, results):\n    results = [result[0] for result in results]\n\n    gold = doc[\"gold\"]\n\n    acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n    completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n    acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n    return {\n        \"acc\": acc,\n        \"acc_norm\": acc_norm,\n    }\n",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "agieval_lsat_rc": {
+      "task": "agieval_lsat_rc",
+      "group": [
+        "agieval",
+        "agieval_nous",
+        "agieval_en"
+      ],
+      "dataset_path": "hails/agieval-lsat-rc",
+      "test_split": "test",
+      "doc_to_text": "{{query}}",
+      "doc_to_target": "{{gold}}",
+      "doc_to_choice": "{{choices}}",
+      "process_results": "def process_results_mcqa(doc, results):\n    results = [result[0] for result in results]\n\n    gold = doc[\"gold\"]\n\n    acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n    completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n    acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n    return {\n        \"acc\": acc,\n        \"acc_norm\": acc_norm,\n    }\n",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "agieval_sat_en": {
+      "task": "agieval_sat_en",
+      "group": [
+        "agieval",
+        "agieval_nous",
+        "agieval_en"
+      ],
+      "dataset_path": "hails/agieval-sat-en",
+      "test_split": "test",
+      "doc_to_text": "{{query}}",
+      "doc_to_target": "{{gold}}",
+      "doc_to_choice": "{{choices}}",
+      "process_results": "def process_results_mcqa(doc, results):\n    results = [result[0] for result in results]\n\n    gold = doc[\"gold\"]\n\n    acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n    completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n    acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n    return {\n        \"acc\": acc,\n        \"acc_norm\": acc_norm,\n    }\n",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "agieval_sat_en_without_passage": {
+      "task": "agieval_sat_en_without_passage",
+      "group": [
+        "agieval",
+        "agieval_nous",
+        "agieval_en"
+      ],
+      "dataset_path": "hails/agieval-sat-en-without-passage",
+      "test_split": "test",
+      "doc_to_text": "{{query}}",
+      "doc_to_target": "{{gold}}",
+      "doc_to_choice": "{{choices}}",
+      "process_results": "def process_results_mcqa(doc, results):\n    results = [result[0] for result in results]\n\n    gold = doc[\"gold\"]\n\n    acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n    completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n    acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n    return {\n        \"acc\": acc,\n        \"acc_norm\": acc_norm,\n    }\n",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    },
+    "agieval_sat_math": {
+      "task": "agieval_sat_math",
+      "group": [
+        "agieval",
+        "agieval_nous",
+        "agieval_en"
+      ],
+      "dataset_path": "hails/agieval-sat-math",
+      "test_split": "test",
+      "doc_to_text": "{{query}}",
+      "doc_to_target": "{{gold}}",
+      "doc_to_choice": "{{choices}}",
+      "process_results": "def process_results_mcqa(doc, results):\n    results = [result[0] for result in results]\n\n    gold = doc[\"gold\"]\n\n    acc = 1.0 if int(np.argmax(results)) in gold else 0.0\n    completion_len = np.array([float(len(i)) for i in doc[\"choices\"]])\n    acc_norm = 1.0 if int(np.argmax(results / completion_len)) in gold else 0.0\n\n    return {\n        \"acc\": acc,\n        \"acc_norm\": acc_norm,\n    }\n",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 0,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    }
+  },
+  "versions": {
+    "agieval_aqua_rat": 1.0,
+    "agieval_logiqa_en": 1.0,
+    "agieval_lsat_ar": 1.0,
+    "agieval_lsat_lr": 1.0,
+    "agieval_lsat_rc": 1.0,
+    "agieval_sat_en": 1.0,
+    "agieval_sat_en_without_passage": 1.0,
+    "agieval_sat_math": 1.0
+  },
+  "n-shot": {
+    "agieval_aqua_rat": 0,
+    "agieval_logiqa_en": 0,
+    "agieval_lsat_ar": 0,
+    "agieval_lsat_lr": 0,
+    "agieval_lsat_rc": 0,
+    "agieval_nous": 0,
+    "agieval_sat_en": 0,
+    "agieval_sat_en_without_passage": 0,
+    "agieval_sat_math": 0
+  },
+  "higher_is_better": {
+    "agieval_aqua_rat": {
+      "acc": true,
+      "acc_norm": true
+    },
+    "agieval_logiqa_en": {
+      "acc": true,
+      "acc_norm": true
+    },
+    "agieval_lsat_ar": {
+      "acc": true,
+      "acc_norm": true
+    },
+    "agieval_lsat_lr": {
+      "acc": true,
+      "acc_norm": true
+    },
+    "agieval_lsat_rc": {
+      "acc": true,
+      "acc_norm": true
+    },
+    "agieval_nous": {
+      "acc": true,
+      "acc_norm": true
+    },
+    "agieval_sat_en": {
+      "acc": true,
+      "acc_norm": true
+    },
+    "agieval_sat_en_without_passage": {
+      "acc": true,
+      "acc_norm": true
+    },
+    "agieval_sat_math": {
+      "acc": true,
+      "acc_norm": true
+    }
+  },
+  "n-samples": {
+    "agieval_sat_en": {
+      "original": 206,
+      "effective": 206
+    },
+    "agieval_lsat_ar": {
+      "original": 230,
+      "effective": 230
+    },
+    "agieval_sat_en_without_passage": {
+      "original": 206,
+      "effective": 206
+    },
+    "agieval_aqua_rat": {
+      "original": 254,
+      "effective": 254
+    },
+    "agieval_logiqa_en": {
+      "original": 651,
+      "effective": 651
+    },
+    "agieval_sat_math": {
+      "original": 220,
+      "effective": 220
+    },
+    "agieval_lsat_rc": {
+      "original": 269,
+      "effective": 269
+    },
+    "agieval_lsat_lr": {
+      "original": 510,
+      "effective": 510
+    }
+  },
+  "config": {
+    "model": "hf",
+    "model_args": "pretrained=/home/migel/Tess-v2.5-qwen2-72B-safetensors,parallelize=True",
+    "model_num_parameters": 72706203648,
+    "model_dtype": "torch.float16",
+    "model_revision": "main",
+    "model_sha": "",
+    "batch_size": "16",
+    "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": "b3e4c49a",
+  "date": 1718163625.5715299,
+  "pretty_env_info": "PyTorch version: 2.3.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 20.04.6 LTS (x86_64)\nGCC version: (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0\nClang version: Could not collect\nCMake version: version 3.29.3\nLibc version: glibc-2.31\n\nPython version: 3.10.14 (main, Apr  6 2024, 18:45:05) [GCC 9.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-1050-azure-x86_64-with-glibc2.31\nIs CUDA available: True\nCUDA runtime version: 12.1.105\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100 80GB PCIe\nGPU 1: NVIDIA A100 80GB PCIe\nGPU 2: NVIDIA A100 80GB PCIe\nGPU 3: NVIDIA A100 80GB PCIe\n\nNvidia driver version: 530.30.02\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\nByte Order:                         Little Endian\nAddress sizes:                      48 bits physical, 48 bits virtual\nCPU(s):                             96\nOn-line CPU(s) list:                0-95\nThread(s) per core:                 1\nCore(s) per socket:                 48\nSocket(s):                          2\nNUMA node(s):                       4\nVendor ID:                          AuthenticAMD\nCPU family:                         25\nModel:                              1\nModel name:                         AMD EPYC 7V13 64-Core Processor\nStepping:                           1\nCPU MHz:                            2445.435\nBogoMIPS:                           4890.87\nHypervisor vendor:                  Microsoft\nVirtualization type:                full\nL1d cache:                          3 MiB\nL1i cache:                          3 MiB\nL2 cache:                           48 MiB\nL3 cache:                           384 MiB\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:             Not affected\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\nVulnerability Spec store bypass:    Vulnerable\nVulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2:           Mitigation; Retpolines, STIBP disabled, RSB filling, PBRSB-eIBRS Not affected\nVulnerability Srbds:                Not affected\nVulnerability Tsx async abort:      Not affected\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 pcid 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 invpcid_single vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves clzero xsaveerptr rdpru arat umip vaes vpclmulqdq rdpid fsrm\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] torch==2.3.0\n[pip3] triton==2.3.0\n[conda] magma-cuda117             2.6.1                         1    pytorch\n[conda] mkl                       2022.2.1                 pypi_0    pypi\n[conda] mkl-include               2022.2.1                 pypi_0    pypi\n[conda] numpy                     1.24.4                   pypi_0    pypi\n[conda] pytorch-lightning         1.9.5                    pypi_0    pypi\n[conda] torch                     2.0.1                    pypi_0    pypi\n[conda] torch-nebula              0.16.10                  pypi_0    pypi\n[conda] torch-ort                 1.17.0                   pypi_0    pypi\n[conda] torchaudio                2.0.2+cu117              pypi_0    pypi\n[conda] torchdata                 0.6.1                    pypi_0    pypi\n[conda] torchmetrics              1.2.0                    pypi_0    pypi\n[conda] torchsnapshot             0.1.0                    pypi_0    pypi\n[conda] torchvision               0.15.2+cu117             pypi_0    pypi\n[conda] triton                    2.0.0                    pypi_0    pypi",
+  "transformers_version": "4.41.1",
+  "upper_git_hash": null,
+  "task_hashes": {},
+  "model_source": "hf",
+  "model_name": "/home/migel/Tess-v2.5-qwen2-72B-safetensors",
+  "model_name_sanitized": "__home__migel__Tess-v2.5-qwen2-72B-safetensors",
+  "system_instruction": null,
+  "system_instruction_sha": null,
+  "chat_template": null,
+  "chat_template_sha": null,
+  "start_time": 377200.61189737,
+  "end_time": 380116.891366629,
+  "total_evaluation_time_seconds": "2916.279469258967"
+}

Evals/Tess-v2.5-Qwen2-72B-hellaswag.json

@@ -0,0 +1,104 @@
+{
+  "results": {
+    "hellaswag": {
+      "acc,none": 0.6811392152957578,
+      "acc_stderr,none": 0.004650825168905212,
+      "acc_norm,none": 0.8729336785500896,
+      "acc_norm_stderr,none": 0.0033236659644120307,
+      "alias": "hellaswag"
+    }
+  },
+  "group_subtasks": {
+    "hellaswag": []
+  },
+  "configs": {
+    "hellaswag": {
+      "task": "hellaswag",
+      "group": [
+        "multiple_choice"
+      ],
+      "dataset_path": "hellaswag",
+      "training_split": "train",
+      "validation_split": "validation",
+      "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n    def _process_doc(doc):\n        ctx = doc[\"ctx_a\"] + \" \" + doc[\"ctx_b\"].capitalize()\n        out_doc = {\n            \"query\": preprocess(doc[\"activity_label\"] + \": \" + ctx),\n            \"choices\": [preprocess(ending) for ending in doc[\"endings\"]],\n            \"gold\": int(doc[\"label\"]),\n        }\n        return out_doc\n\n    return dataset.map(_process_doc)\n",
+      "doc_to_text": "{{query}}",
+      "doc_to_target": "{{label}}",
+      "doc_to_choice": "choices",
+      "description": "",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "num_fewshot": 10,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        },
+        {
+          "metric": "acc_norm",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 1.0
+      }
+    }
+  },
+  "versions": {
+    "hellaswag": 1.0
+  },
+  "n-shot": {
+    "hellaswag": 10
+  },
+  "higher_is_better": {
+    "hellaswag": {
+      "acc": true,
+      "acc_norm": true
+    }
+  },
+  "n-samples": {
+    "hellaswag": {
+      "original": 10042,
+      "effective": 10042
+    }
+  },
+  "config": {
+    "model": "hf",
+    "model_args": "pretrained=/home/migel/Tess-v2.5-qwen2-72B-safetensors,parallelize=True",
+    "model_num_parameters": 72706203648,
+    "model_dtype": "torch.float16",
+    "model_revision": "main",
+    "model_sha": "",
+    "batch_size": "8",
+    "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": "b3e4c49a",
+  "date": 1718190545.705119,
+  "pretty_env_info": "PyTorch version: 2.3.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 20.04.6 LTS (x86_64)\nGCC version: (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0\nClang version: Could not collect\nCMake version: version 3.29.3\nLibc version: glibc-2.31\n\nPython version: 3.10.14 (main, Apr  6 2024, 18:45:05) [GCC 9.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-1050-azure-x86_64-with-glibc2.31\nIs CUDA available: True\nCUDA runtime version: 12.1.105\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100 80GB PCIe\nGPU 1: NVIDIA A100 80GB PCIe\nGPU 2: NVIDIA A100 80GB PCIe\nGPU 3: NVIDIA A100 80GB PCIe\n\nNvidia driver version: 530.30.02\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\nByte Order:                         Little Endian\nAddress sizes:                      48 bits physical, 48 bits virtual\nCPU(s):                             96\nOn-line CPU(s) list:                0-95\nThread(s) per core:                 1\nCore(s) per socket:                 48\nSocket(s):                          2\nNUMA node(s):                       4\nVendor ID:                          AuthenticAMD\nCPU family:                         25\nModel:                              1\nModel name:                         AMD EPYC 7V13 64-Core Processor\nStepping:                           1\nCPU MHz:                            2445.435\nBogoMIPS:                           4890.87\nHypervisor vendor:                  Microsoft\nVirtualization type:                full\nL1d cache:                          3 MiB\nL1i cache:                          3 MiB\nL2 cache:                           48 MiB\nL3 cache:                           384 MiB\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:             Not affected\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\nVulnerability Spec store bypass:    Vulnerable\nVulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2:           Mitigation; Retpolines, STIBP disabled, RSB filling, PBRSB-eIBRS Not affected\nVulnerability Srbds:                Not affected\nVulnerability Tsx async abort:      Not affected\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 pcid 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 invpcid_single vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves clzero xsaveerptr rdpru arat umip vaes vpclmulqdq rdpid fsrm\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] torch==2.3.0\n[pip3] triton==2.3.0\n[conda] magma-cuda117             2.6.1                         1    pytorch\n[conda] mkl                       2022.2.1                 pypi_0    pypi\n[conda] mkl-include               2022.2.1                 pypi_0    pypi\n[conda] numpy                     1.24.4                   pypi_0    pypi\n[conda] pytorch-lightning         1.9.5                    pypi_0    pypi\n[conda] torch                     2.0.1                    pypi_0    pypi\n[conda] torch-nebula              0.16.10                  pypi_0    pypi\n[conda] torch-ort                 1.17.0                   pypi_0    pypi\n[conda] torchaudio                2.0.2+cu117              pypi_0    pypi\n[conda] torchdata                 0.6.1                    pypi_0    pypi\n[conda] torchmetrics              1.2.0                    pypi_0    pypi\n[conda] torchsnapshot             0.1.0                    pypi_0    pypi\n[conda] torchvision               0.15.2+cu117             pypi_0    pypi\n[conda] triton                    2.0.0                    pypi_0    pypi",
+  "transformers_version": "4.41.1",
+  "upper_git_hash": null,
+  "task_hashes": {},
+  "model_source": "hf",
+  "model_name": "/home/migel/Tess-v2.5-qwen2-72B-safetensors",
+  "model_name_sanitized": "__home__migel__Tess-v2.5-qwen2-72B-safetensors",
+  "system_instruction": null,
+  "system_instruction_sha": null,
+  "chat_template": null,
+  "chat_template_sha": null,
+  "start_time": 404120.678699121,
+  "end_time": 430406.206534399,
+  "total_evaluation_time_seconds": "26285.527835278015"
+}

Evals/Tess-v2.5-Qwen2-72B-mmlu.json

@@ -0,0 +1,3158 @@
+{
+  "results": {
+    "mmlu": {
+      "acc,none": 0.8439680957128615,
+      "acc_stderr,none": 0.0029499711040394372,
+      "alias": "mmlu"
+    },
+    "mmlu_humanities": {
+      "alias": " - humanities",
+      "acc,none": 0.8146652497343252,
+      "acc_stderr,none": 0.005505402478774841
+    },
+    "mmlu_formal_logic": {
+      "alias": "  - formal_logic",
+      "acc,none": 0.7301587301587301,
+      "acc_stderr,none": 0.03970158273235173
+    },
+    "mmlu_high_school_european_history": {
+      "alias": "  - high_school_european_history",
+      "acc,none": 0.8909090909090909,
+      "acc_stderr,none": 0.02434383813514564
+    },
+    "mmlu_high_school_us_history": {
+      "alias": "  - high_school_us_history",
+      "acc,none": 0.9509803921568627,
+      "acc_stderr,none": 0.01515383934021267
+    },
+    "mmlu_high_school_world_history": {
+      "alias": "  - high_school_world_history",
+      "acc,none": 0.9409282700421941,
+      "acc_stderr,none": 0.01534659746388869
+    },
+    "mmlu_international_law": {
+      "alias": "  - international_law",
+      "acc,none": 0.9173553719008265,
+      "acc_stderr,none": 0.025135382356604227
+    },
+    "mmlu_jurisprudence": {
+      "alias": "  - jurisprudence",
+      "acc,none": 0.8796296296296297,
+      "acc_stderr,none": 0.031457038543062525
+    },
+    "mmlu_logical_fallacies": {
+      "alias": "  - logical_fallacies",
+      "acc,none": 0.901840490797546,
+      "acc_stderr,none": 0.023376180231059605
+    },
+    "mmlu_moral_disputes": {
+      "alias": "  - moral_disputes",
+      "acc,none": 0.869942196531792,
+      "acc_stderr,none": 0.01810939152822133
+    },
+    "mmlu_moral_scenarios": {
+      "alias": "  - moral_scenarios",
+      "acc,none": 0.829050279329609,
+      "acc_stderr,none": 0.012590873868789222
+    },
+    "mmlu_philosophy": {
+      "alias": "  - philosophy",
+      "acc,none": 0.8713826366559485,
+      "acc_stderr,none": 0.01901399630412152
+    },
+    "mmlu_prehistory": {
+      "alias": "  - prehistory",
+      "acc,none": 0.9104938271604939,
+      "acc_stderr,none": 0.015884141073937555
+    },
+    "mmlu_professional_law": {
+      "alias": "  - professional_law",
+      "acc,none": 0.6929595827900913,
+      "acc_stderr,none": 0.011780959114513764
+    },
+    "mmlu_world_religions": {
+      "alias": "  - world_religions",
+      "acc,none": 0.8888888888888888,
+      "acc_stderr,none": 0.024103384202072864
+    },
+    "mmlu_other": {
+      "alias": " - other",
+      "acc,none": 0.8625683939491471,
+      "acc_stderr,none": 0.005895325056685939
+    },
+    "mmlu_business_ethics": {
+      "alias": "  - business_ethics",
+      "acc,none": 0.78,
+      "acc_stderr,none": 0.04163331998932263
+    },
+    "mmlu_clinical_knowledge": {
+      "alias": "  - clinical_knowledge",
+      "acc,none": 0.8716981132075472,
+      "acc_stderr,none": 0.02058247568799185
+    },
+    "mmlu_college_medicine": {
+      "alias": "  - college_medicine",
+      "acc,none": 0.8323699421965318,
+      "acc_stderr,none": 0.028481963032143395
+    },
+    "mmlu_global_facts": {
+      "alias": "  - global_facts",
+      "acc,none": 0.61,
+      "acc_stderr,none": 0.04902071300001975
+    },
+    "mmlu_human_aging": {
+      "alias": "  - human_aging",
+      "acc,none": 0.8565022421524664,
+      "acc_stderr,none": 0.0235293712696182
+    },
+    "mmlu_management": {
+      "alias": "  - management",
+      "acc,none": 0.9223300970873787,
+      "acc_stderr,none": 0.026501440784762766
+    },
+    "mmlu_marketing": {
+      "alias": "  - marketing",
+      "acc,none": 0.9487179487179487,
+      "acc_stderr,none": 0.014450181176872726
+    },
+    "mmlu_medical_genetics": {
+      "alias": "  - medical_genetics",
+      "acc,none": 0.9,
+      "acc_stderr,none": 0.030151134457776348
+    },
+    "mmlu_miscellaneous": {
+      "alias": "  - miscellaneous",
+      "acc,none": 0.9501915708812261,
+      "acc_stderr,none": 0.0077795348866793465
+    },
+    "mmlu_nutrition": {
+      "alias": "  - nutrition",
+      "acc,none": 0.9019607843137255,
+      "acc_stderr,none": 0.017027222935582193
+    },
+    "mmlu_professional_accounting": {
+      "alias": "  - professional_accounting",
+      "acc,none": 0.75177304964539,
+      "acc_stderr,none": 0.025770015644290392
+    },
+    "mmlu_professional_medicine": {
+      "alias": "  - professional_medicine",
+      "acc,none": 0.8897058823529411,
+      "acc_stderr,none": 0.019028947191474497
+    },
+    "mmlu_virology": {
+      "alias": "  - virology",
+      "acc,none": 0.5662650602409639,
+      "acc_stderr,none": 0.03858158940685517
+    },
+    "mmlu_social_sciences": {
+      "alias": " - social_sciences",
+      "acc,none": 0.9038024049398765,
+      "acc_stderr,none": 0.005221504585802578
+    },
+    "mmlu_econometrics": {
+      "alias": "  - econometrics",
+      "acc,none": 0.7280701754385965,
+      "acc_stderr,none": 0.041857744240220554
+    },
+    "mmlu_high_school_geography": {
+      "alias": "  - high_school_geography",
+      "acc,none": 0.9393939393939394,
+      "acc_stderr,none": 0.016999994927421606
+    },
+    "mmlu_high_school_government_and_politics": {
+      "alias": "  - high_school_government_and_politics",
+      "acc,none": 0.9896373056994818,
+      "acc_stderr,none": 0.007308424386792201
+    },
+    "mmlu_high_school_macroeconomics": {
+      "alias": "  - high_school_macroeconomics",
+      "acc,none": 0.8897435897435897,
+      "acc_stderr,none": 0.015880331261056115
+    },
+    "mmlu_high_school_microeconomics": {
+      "alias": "  - high_school_microeconomics",
+      "acc,none": 0.9411764705882353,
+      "acc_stderr,none": 0.015283995352038402
+    },
+    "mmlu_high_school_psychology": {
+      "alias": "  - high_school_psychology",
+      "acc,none": 0.9357798165137615,
+      "acc_stderr,none": 0.010510494713201424
+    },
+    "mmlu_human_sexuality": {
+      "alias": "  - human_sexuality",
+      "acc,none": 0.9083969465648855,
+      "acc_stderr,none": 0.025300035578642965
+    },
+    "mmlu_professional_psychology": {
+      "alias": "  - professional_psychology",
+      "acc,none": 0.8970588235294118,
+      "acc_stderr,none": 0.012293751200845176
+    },
+    "mmlu_public_relations": {
+      "alias": "  - public_relations",
+      "acc,none": 0.7454545454545455,
+      "acc_stderr,none": 0.041723430387053825
+    },
+    "mmlu_security_studies": {
+      "alias": "  - security_studies",
+      "acc,none": 0.8408163265306122,
+      "acc_stderr,none": 0.023420972069166365
+    },
+    "mmlu_sociology": {
+      "alias": "  - sociology",
+      "acc,none": 0.945273631840796,
+      "acc_stderr,none": 0.016082815796263254
+    },
+    "mmlu_us_foreign_policy": {
+      "alias": "  - us_foreign_policy",
+      "acc,none": 0.94,
+      "acc_stderr,none": 0.02386832565759419
+    },
+    "mmlu_stem": {
+      "alias": " - stem",
+      "acc,none": 0.8109736758642563,
+      "acc_stderr,none": 0.0067376135296805745
+    },
+    "mmlu_abstract_algebra": {
+      "alias": "  - abstract_algebra",
+      "acc,none": 0.66,
+      "acc_stderr,none": 0.04760952285695237
+    },
+    "mmlu_anatomy": {
+      "alias": "  - anatomy",
+      "acc,none": 0.7925925925925926,
+      "acc_stderr,none": 0.03502553170678317
+    },
+    "mmlu_astronomy": {
+      "alias": "  - astronomy",
+      "acc,none": 0.9276315789473685,
+      "acc_stderr,none": 0.021085011261884112
+    },
+    "mmlu_college_biology": {
+      "alias": "  - college_biology",
+      "acc,none": 0.9444444444444444,
+      "acc_stderr,none": 0.01915507853243362
+    },
+    "mmlu_college_chemistry": {
+      "alias": "  - college_chemistry",
+      "acc,none": 0.58,
+      "acc_stderr,none": 0.049604496374885836
+    },
+    "mmlu_college_computer_science": {
+      "alias": "  - college_computer_science",
+      "acc,none": 0.8,
+      "acc_stderr,none": 0.040201512610368445
+    },
+    "mmlu_college_mathematics": {
+      "alias": "  - college_mathematics",
+      "acc,none": 0.63,
+      "acc_stderr,none": 0.04852365870939099
+    },
+    "mmlu_college_physics": {
+      "alias": "  - college_physics",
+      "acc,none": 0.6470588235294118,
+      "acc_stderr,none": 0.04755129616062947
+    },
+    "mmlu_computer_security": {
+      "alias": "  - computer_security",
+      "acc,none": 0.83,
+      "acc_stderr,none": 0.0377525168068637
+    },
+    "mmlu_conceptual_physics": {
+      "alias": "  - conceptual_physics",
+      "acc,none": 0.8893617021276595,
+      "acc_stderr,none": 0.020506145099008433
+    },
+    "mmlu_electrical_engineering": {
+      "alias": "  - electrical_engineering",
+      "acc,none": 0.8275862068965517,
+      "acc_stderr,none": 0.03147830790259575
+    },
+    "mmlu_elementary_mathematics": {
+      "alias": "  - elementary_mathematics",
+      "acc,none": 0.8888888888888888,
+      "acc_stderr,none": 0.01618571201620511
+    },
+    "mmlu_high_school_biology": {
+      "alias": "  - high_school_biology",
+      "acc,none": 0.9419354838709677,
+      "acc_stderr,none": 0.01330413811280927
+    },
+    "mmlu_high_school_chemistry": {
+      "alias": "  - high_school_chemistry",
+      "acc,none": 0.7980295566502463,
+      "acc_stderr,none": 0.028247350122180243
+    },
+    "mmlu_high_school_computer_science": {
+      "alias": "  - high_school_computer_science",
+      "acc,none": 0.91,
+      "acc_stderr,none": 0.028762349126466115
+    },
+    "mmlu_high_school_mathematics": {
+      "alias": "  - high_school_mathematics",
+      "acc,none": 0.6777777777777778,
+      "acc_stderr,none": 0.028493465091028597
+    },
+    "mmlu_high_school_physics": {
+      "alias": "  - high_school_physics",
+      "acc,none": 0.7284768211920529,
+      "acc_stderr,none": 0.03631329803969654
+    },
+    "mmlu_high_school_statistics": {
+      "alias": "  - high_school_statistics",
+      "acc,none": 0.7824074074074074,
+      "acc_stderr,none": 0.028139689444859676
+    },
+    "mmlu_machine_learning": {
+      "alias": "  - machine_learning",
+      "acc,none": 0.7589285714285714,
+      "acc_stderr,none": 0.04059867246952685
+    }
+  },
+  "groups": {
+    "mmlu": {
+      "acc,none": 0.8439680957128615,
+      "acc_stderr,none": 0.0029499711040394372,
+      "alias": "mmlu"
+    },
+    "mmlu_humanities": {
+      "alias": " - humanities",
+      "acc,none": 0.8146652497343252,
+      "acc_stderr,none": 0.005505402478774841
+    },
+    "mmlu_other": {
+      "alias": " - other",
+      "acc,none": 0.8625683939491471,
+      "acc_stderr,none": 0.005895325056685939
+    },
+    "mmlu_social_sciences": {
+      "alias": " - social_sciences",
+      "acc,none": 0.9038024049398765,
+      "acc_stderr,none": 0.005221504585802578
+    },
+    "mmlu_stem": {
+      "alias": " - stem",
+      "acc,none": 0.8109736758642563,
+      "acc_stderr,none": 0.0067376135296805745
+    }
+  },
+  "group_subtasks": {
+    "mmlu_stem": [
+      "mmlu_college_biology",
+      "mmlu_high_school_computer_science",
+      "mmlu_elementary_mathematics",
+      "mmlu_astronomy",
+      "mmlu_machine_learning",
+      "mmlu_high_school_mathematics",
+      "mmlu_electrical_engineering",
+      "mmlu_college_chemistry",
+      "mmlu_college_mathematics",
+      "mmlu_high_school_statistics",
+      "mmlu_high_school_biology",
+      "mmlu_abstract_algebra",
+      "mmlu_college_physics",
+      "mmlu_conceptual_physics",
+      "mmlu_computer_security",
+      "mmlu_anatomy",
+      "mmlu_college_computer_science",
+      "mmlu_high_school_physics",
+      "mmlu_high_school_chemistry"
+    ],
+    "mmlu_other": [
+      "mmlu_marketing",
+      "mmlu_professional_accounting",
+      "mmlu_clinical_knowledge",
+      "mmlu_college_medicine",
+      "mmlu_miscellaneous",
+      "mmlu_virology",
+      "mmlu_business_ethics",
+      "mmlu_professional_medicine",
+      "mmlu_global_facts",
+      "mmlu_nutrition",
+      "mmlu_human_aging",
+      "mmlu_management",
+      "mmlu_medical_genetics"
+    ],
+    "mmlu_social_sciences": [
+      "mmlu_high_school_psychology",
+      "mmlu_high_school_geography",
+      "mmlu_high_school_macroeconomics",
+      "mmlu_public_relations",
+      "mmlu_security_studies",
+      "mmlu_high_school_microeconomics",
+      "mmlu_human_sexuality",
+      "mmlu_sociology",
+      "mmlu_professional_psychology",
+      "mmlu_econometrics",
+      "mmlu_us_foreign_policy",
+      "mmlu_high_school_government_and_politics"
+    ],
+    "mmlu_humanities": [
+      "mmlu_moral_scenarios",
+      "mmlu_high_school_us_history",
+      "mmlu_high_school_world_history",
+      "mmlu_world_religions",
+      "mmlu_formal_logic",
+      "mmlu_moral_disputes",
+      "mmlu_prehistory",
+      "mmlu_international_law",
+      "mmlu_logical_fallacies",
+      "mmlu_professional_law",
+      "mmlu_philosophy",
+      "mmlu_high_school_european_history",
+      "mmlu_jurisprudence"
+    ],
+    "mmlu": [
+      "mmlu_humanities",
+      "mmlu_social_sciences",
+      "mmlu_other",
+      "mmlu_stem"
+    ]
+  },
+  "configs": {
+    "mmlu_abstract_algebra": {
+      "task": "mmlu_abstract_algebra",
+      "task_alias": "abstract_algebra",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "abstract_algebra",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about abstract algebra.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_anatomy": {
+      "task": "mmlu_anatomy",
+      "task_alias": "anatomy",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "anatomy",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about anatomy.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_astronomy": {
+      "task": "mmlu_astronomy",
+      "task_alias": "astronomy",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "astronomy",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about astronomy.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_business_ethics": {
+      "task": "mmlu_business_ethics",
+      "task_alias": "business_ethics",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "business_ethics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about business ethics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_clinical_knowledge": {
+      "task": "mmlu_clinical_knowledge",
+      "task_alias": "clinical_knowledge",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "clinical_knowledge",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about clinical knowledge.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_college_biology": {
+      "task": "mmlu_college_biology",
+      "task_alias": "college_biology",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "college_biology",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about college biology.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_college_chemistry": {
+      "task": "mmlu_college_chemistry",
+      "task_alias": "college_chemistry",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "college_chemistry",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about college chemistry.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_college_computer_science": {
+      "task": "mmlu_college_computer_science",
+      "task_alias": "college_computer_science",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "college_computer_science",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about college computer science.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_college_mathematics": {
+      "task": "mmlu_college_mathematics",
+      "task_alias": "college_mathematics",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "college_mathematics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about college mathematics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_college_medicine": {
+      "task": "mmlu_college_medicine",
+      "task_alias": "college_medicine",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "college_medicine",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about college medicine.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_college_physics": {
+      "task": "mmlu_college_physics",
+      "task_alias": "college_physics",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "college_physics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about college physics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_computer_security": {
+      "task": "mmlu_computer_security",
+      "task_alias": "computer_security",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "computer_security",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about computer security.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_conceptual_physics": {
+      "task": "mmlu_conceptual_physics",
+      "task_alias": "conceptual_physics",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "conceptual_physics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about conceptual physics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_econometrics": {
+      "task": "mmlu_econometrics",
+      "task_alias": "econometrics",
+      "group": "mmlu_social_sciences",
+      "group_alias": "social_sciences",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "econometrics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about econometrics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_electrical_engineering": {
+      "task": "mmlu_electrical_engineering",
+      "task_alias": "electrical_engineering",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "electrical_engineering",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about electrical engineering.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_elementary_mathematics": {
+      "task": "mmlu_elementary_mathematics",
+      "task_alias": "elementary_mathematics",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "elementary_mathematics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about elementary mathematics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_formal_logic": {
+      "task": "mmlu_formal_logic",
+      "task_alias": "formal_logic",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "formal_logic",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about formal logic.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_global_facts": {
+      "task": "mmlu_global_facts",
+      "task_alias": "global_facts",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "global_facts",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about global facts.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_biology": {
+      "task": "mmlu_high_school_biology",
+      "task_alias": "high_school_biology",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_biology",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school biology.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_chemistry": {
+      "task": "mmlu_high_school_chemistry",
+      "task_alias": "high_school_chemistry",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_chemistry",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school chemistry.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_computer_science": {
+      "task": "mmlu_high_school_computer_science",
+      "task_alias": "high_school_computer_science",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_computer_science",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school computer science.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_european_history": {
+      "task": "mmlu_high_school_european_history",
+      "task_alias": "high_school_european_history",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_european_history",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school european history.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_geography": {
+      "task": "mmlu_high_school_geography",
+      "task_alias": "high_school_geography",
+      "group": "mmlu_social_sciences",
+      "group_alias": "social_sciences",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_geography",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school geography.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_government_and_politics": {
+      "task": "mmlu_high_school_government_and_politics",
+      "task_alias": "high_school_government_and_politics",
+      "group": "mmlu_social_sciences",
+      "group_alias": "social_sciences",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_government_and_politics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school government and politics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_macroeconomics": {
+      "task": "mmlu_high_school_macroeconomics",
+      "task_alias": "high_school_macroeconomics",
+      "group": "mmlu_social_sciences",
+      "group_alias": "social_sciences",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_macroeconomics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school macroeconomics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_mathematics": {
+      "task": "mmlu_high_school_mathematics",
+      "task_alias": "high_school_mathematics",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_mathematics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school mathematics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_microeconomics": {
+      "task": "mmlu_high_school_microeconomics",
+      "task_alias": "high_school_microeconomics",
+      "group": "mmlu_social_sciences",
+      "group_alias": "social_sciences",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_microeconomics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school microeconomics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_physics": {
+      "task": "mmlu_high_school_physics",
+      "task_alias": "high_school_physics",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_physics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school physics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_psychology": {
+      "task": "mmlu_high_school_psychology",
+      "task_alias": "high_school_psychology",
+      "group": "mmlu_social_sciences",
+      "group_alias": "social_sciences",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_psychology",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school psychology.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_statistics": {
+      "task": "mmlu_high_school_statistics",
+      "task_alias": "high_school_statistics",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_statistics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school statistics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_us_history": {
+      "task": "mmlu_high_school_us_history",
+      "task_alias": "high_school_us_history",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_us_history",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school us history.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_high_school_world_history": {
+      "task": "mmlu_high_school_world_history",
+      "task_alias": "high_school_world_history",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "high_school_world_history",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about high school world history.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_human_aging": {
+      "task": "mmlu_human_aging",
+      "task_alias": "human_aging",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "human_aging",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about human aging.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_human_sexuality": {
+      "task": "mmlu_human_sexuality",
+      "task_alias": "human_sexuality",
+      "group": "mmlu_social_sciences",
+      "group_alias": "social_sciences",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "human_sexuality",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about human sexuality.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_international_law": {
+      "task": "mmlu_international_law",
+      "task_alias": "international_law",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "international_law",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about international law.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_jurisprudence": {
+      "task": "mmlu_jurisprudence",
+      "task_alias": "jurisprudence",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "jurisprudence",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about jurisprudence.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_logical_fallacies": {
+      "task": "mmlu_logical_fallacies",
+      "task_alias": "logical_fallacies",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "logical_fallacies",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about logical fallacies.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_machine_learning": {
+      "task": "mmlu_machine_learning",
+      "task_alias": "machine_learning",
+      "group": "mmlu_stem",
+      "group_alias": "stem",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "machine_learning",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about machine learning.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_management": {
+      "task": "mmlu_management",
+      "task_alias": "management",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "management",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about management.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_marketing": {
+      "task": "mmlu_marketing",
+      "task_alias": "marketing",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "marketing",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about marketing.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_medical_genetics": {
+      "task": "mmlu_medical_genetics",
+      "task_alias": "medical_genetics",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "medical_genetics",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about medical genetics.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_miscellaneous": {
+      "task": "mmlu_miscellaneous",
+      "task_alias": "miscellaneous",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "miscellaneous",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about miscellaneous.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_moral_disputes": {
+      "task": "mmlu_moral_disputes",
+      "task_alias": "moral_disputes",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "moral_disputes",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about moral disputes.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_moral_scenarios": {
+      "task": "mmlu_moral_scenarios",
+      "task_alias": "moral_scenarios",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "moral_scenarios",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about moral scenarios.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_nutrition": {
+      "task": "mmlu_nutrition",
+      "task_alias": "nutrition",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "nutrition",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about nutrition.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_philosophy": {
+      "task": "mmlu_philosophy",
+      "task_alias": "philosophy",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "philosophy",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about philosophy.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_prehistory": {
+      "task": "mmlu_prehistory",
+      "task_alias": "prehistory",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "prehistory",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about prehistory.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_professional_accounting": {
+      "task": "mmlu_professional_accounting",
+      "task_alias": "professional_accounting",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "professional_accounting",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about professional accounting.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_professional_law": {
+      "task": "mmlu_professional_law",
+      "task_alias": "professional_law",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "professional_law",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about professional law.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_professional_medicine": {
+      "task": "mmlu_professional_medicine",
+      "task_alias": "professional_medicine",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "professional_medicine",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about professional medicine.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_professional_psychology": {
+      "task": "mmlu_professional_psychology",
+      "task_alias": "professional_psychology",
+      "group": "mmlu_social_sciences",
+      "group_alias": "social_sciences",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "professional_psychology",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about professional psychology.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_public_relations": {
+      "task": "mmlu_public_relations",
+      "task_alias": "public_relations",
+      "group": "mmlu_social_sciences",
+      "group_alias": "social_sciences",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "public_relations",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about public relations.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_security_studies": {
+      "task": "mmlu_security_studies",
+      "task_alias": "security_studies",
+      "group": "mmlu_social_sciences",
+      "group_alias": "social_sciences",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "security_studies",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about security studies.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_sociology": {
+      "task": "mmlu_sociology",
+      "task_alias": "sociology",
+      "group": "mmlu_social_sciences",
+      "group_alias": "social_sciences",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "sociology",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about sociology.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_us_foreign_policy": {
+      "task": "mmlu_us_foreign_policy",
+      "task_alias": "us_foreign_policy",
+      "group": "mmlu_social_sciences",
+      "group_alias": "social_sciences",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "us_foreign_policy",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about us foreign policy.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_virology": {
+      "task": "mmlu_virology",
+      "task_alias": "virology",
+      "group": "mmlu_other",
+      "group_alias": "other",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "virology",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about virology.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    },
+    "mmlu_world_religions": {
+      "task": "mmlu_world_religions",
+      "task_alias": "world_religions",
+      "group": "mmlu_humanities",
+      "group_alias": "humanities",
+      "dataset_path": "hails/mmlu_no_train",
+      "dataset_name": "world_religions",
+      "test_split": "test",
+      "fewshot_split": "dev",
+      "doc_to_text": "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:",
+      "doc_to_target": "answer",
+      "doc_to_choice": [
+        "A",
+        "B",
+        "C",
+        "D"
+      ],
+      "description": "The following are multiple choice questions (with answers) about world religions.\n\n",
+      "target_delimiter": " ",
+      "fewshot_delimiter": "\n\n",
+      "fewshot_config": {
+        "sampler": "first_n"
+      },
+      "num_fewshot": 5,
+      "metric_list": [
+        {
+          "metric": "acc",
+          "aggregation": "mean",
+          "higher_is_better": true
+        }
+      ],
+      "output_type": "multiple_choice",
+      "repeats": 1,
+      "should_decontaminate": false,
+      "metadata": {
+        "version": 0.0
+      }
+    }
+  },
+  "versions": {
+    "mmlu_abstract_algebra": 0.0,
+    "mmlu_anatomy": 0.0,
+    "mmlu_astronomy": 0.0,
+    "mmlu_business_ethics": 0.0,
+    "mmlu_clinical_knowledge": 0.0,
+    "mmlu_college_biology": 0.0,
+    "mmlu_college_chemistry": 0.0,
+    "mmlu_college_computer_science": 0.0,
+    "mmlu_college_mathematics": 0.0,
+    "mmlu_college_medicine": 0.0,
+    "mmlu_college_physics": 0.0,
+    "mmlu_computer_security": 0.0,
+    "mmlu_conceptual_physics": 0.0,
+    "mmlu_econometrics": 0.0,
+    "mmlu_electrical_engineering": 0.0,
+    "mmlu_elementary_mathematics": 0.0,
+    "mmlu_formal_logic": 0.0,
+    "mmlu_global_facts": 0.0,
+    "mmlu_high_school_biology": 0.0,
+    "mmlu_high_school_chemistry": 0.0,
+    "mmlu_high_school_computer_science": 0.0,
+    "mmlu_high_school_european_history": 0.0,
+    "mmlu_high_school_geography": 0.0,
+    "mmlu_high_school_government_and_politics": 0.0,
+    "mmlu_high_school_macroeconomics": 0.0,
+    "mmlu_high_school_mathematics": 0.0,
+    "mmlu_high_school_microeconomics": 0.0,
+    "mmlu_high_school_physics": 0.0,
+    "mmlu_high_school_psychology": 0.0,
+    "mmlu_high_school_statistics": 0.0,
+    "mmlu_high_school_us_history": 0.0,
+    "mmlu_high_school_world_history": 0.0,
+    "mmlu_human_aging": 0.0,
+    "mmlu_human_sexuality": 0.0,
+    "mmlu_international_law": 0.0,
+    "mmlu_jurisprudence": 0.0,
+    "mmlu_logical_fallacies": 0.0,
+    "mmlu_machine_learning": 0.0,
+    "mmlu_management": 0.0,
+    "mmlu_marketing": 0.0,
+    "mmlu_medical_genetics": 0.0,
+    "mmlu_miscellaneous": 0.0,
+    "mmlu_moral_disputes": 0.0,
+    "mmlu_moral_scenarios": 0.0,
+    "mmlu_nutrition": 0.0,
+    "mmlu_philosophy": 0.0,
+    "mmlu_prehistory": 0.0,
+    "mmlu_professional_accounting": 0.0,
+    "mmlu_professional_law": 0.0,
+    "mmlu_professional_medicine": 0.0,
+    "mmlu_professional_psychology": 0.0,
+    "mmlu_public_relations": 0.0,
+    "mmlu_security_studies": 0.0,
+    "mmlu_sociology": 0.0,
+    "mmlu_us_foreign_policy": 0.0,
+    "mmlu_virology": 0.0,
+    "mmlu_world_religions": 0.0
+  },
+  "n-shot": {
+    "mmlu": 0,
+    "mmlu_abstract_algebra": 5,
+    "mmlu_anatomy": 5,
+    "mmlu_astronomy": 5,
+    "mmlu_business_ethics": 5,
+    "mmlu_clinical_knowledge": 5,
+    "mmlu_college_biology": 5,
+    "mmlu_college_chemistry": 5,
+    "mmlu_college_computer_science": 5,
+    "mmlu_college_mathematics": 5,
+    "mmlu_college_medicine": 5,
+    "mmlu_college_physics": 5,
+    "mmlu_computer_security": 5,
+    "mmlu_conceptual_physics": 5,
+    "mmlu_econometrics": 5,
+    "mmlu_electrical_engineering": 5,
+    "mmlu_elementary_mathematics": 5,
+    "mmlu_formal_logic": 5,
+    "mmlu_global_facts": 5,
+    "mmlu_high_school_biology": 5,
+    "mmlu_high_school_chemistry": 5,
+    "mmlu_high_school_computer_science": 5,
+    "mmlu_high_school_european_history": 5,
+    "mmlu_high_school_geography": 5,
+    "mmlu_high_school_government_and_politics": 5,
+    "mmlu_high_school_macroeconomics": 5,
+    "mmlu_high_school_mathematics": 5,
+    "mmlu_high_school_microeconomics": 5,
+    "mmlu_high_school_physics": 5,
+    "mmlu_high_school_psychology": 5,
+    "mmlu_high_school_statistics": 5,
+    "mmlu_high_school_us_history": 5,
+    "mmlu_high_school_world_history": 5,
+    "mmlu_human_aging": 5,
+    "mmlu_human_sexuality": 5,
+    "mmlu_humanities": 5,
+    "mmlu_international_law": 5,
+    "mmlu_jurisprudence": 5,
+    "mmlu_logical_fallacies": 5,
+    "mmlu_machine_learning": 5,
+    "mmlu_management": 5,
+    "mmlu_marketing": 5,
+    "mmlu_medical_genetics": 5,
+    "mmlu_miscellaneous": 5,
+    "mmlu_moral_disputes": 5,
+    "mmlu_moral_scenarios": 5,
+    "mmlu_nutrition": 5,
+    "mmlu_other": 5,
+    "mmlu_philosophy": 5,
+    "mmlu_prehistory": 5,
+    "mmlu_professional_accounting": 5,
+    "mmlu_professional_law": 5,
+    "mmlu_professional_medicine": 5,
+    "mmlu_professional_psychology": 5,
+    "mmlu_public_relations": 5,
+    "mmlu_security_studies": 5,
+    "mmlu_social_sciences": 5,
+    "mmlu_sociology": 5,
+    "mmlu_stem": 5,
+    "mmlu_us_foreign_policy": 5,
+    "mmlu_virology": 5,
+    "mmlu_world_religions": 5
+  },
+  "higher_is_better": {
+    "mmlu": {
+      "acc": true
+    },
+    "mmlu_abstract_algebra": {
+      "acc": true
+    },
+    "mmlu_anatomy": {
+      "acc": true
+    },
+    "mmlu_astronomy": {
+      "acc": true
+    },
+    "mmlu_business_ethics": {
+      "acc": true
+    },
+    "mmlu_clinical_knowledge": {
+      "acc": true
+    },
+    "mmlu_college_biology": {
+      "acc": true
+    },
+    "mmlu_college_chemistry": {
+      "acc": true
+    },
+    "mmlu_college_computer_science": {
+      "acc": true
+    },
+    "mmlu_college_mathematics": {
+      "acc": true
+    },
+    "mmlu_college_medicine": {
+      "acc": true
+    },
+    "mmlu_college_physics": {
+      "acc": true
+    },
+    "mmlu_computer_security": {
+      "acc": true
+    },
+    "mmlu_conceptual_physics": {
+      "acc": true
+    },
+    "mmlu_econometrics": {
+      "acc": true
+    },
+    "mmlu_electrical_engineering": {
+      "acc": true
+    },
+    "mmlu_elementary_mathematics": {
+      "acc": true
+    },
+    "mmlu_formal_logic": {
+      "acc": true
+    },
+    "mmlu_global_facts": {
+      "acc": true
+    },
+    "mmlu_high_school_biology": {
+      "acc": true
+    },
+    "mmlu_high_school_chemistry": {
+      "acc": true
+    },
+    "mmlu_high_school_computer_science": {
+      "acc": true
+    },
+    "mmlu_high_school_european_history": {
+      "acc": true
+    },
+    "mmlu_high_school_geography": {
+      "acc": true
+    },
+    "mmlu_high_school_government_and_politics": {
+      "acc": true
+    },
+    "mmlu_high_school_macroeconomics": {
+      "acc": true
+    },
+    "mmlu_high_school_mathematics": {
+      "acc": true
+    },
+    "mmlu_high_school_microeconomics": {
+      "acc": true
+    },
+    "mmlu_high_school_physics": {
+      "acc": true
+    },
+    "mmlu_high_school_psychology": {
+      "acc": true
+    },
+    "mmlu_high_school_statistics": {
+      "acc": true
+    },
+    "mmlu_high_school_us_history": {
+      "acc": true
+    },
+    "mmlu_high_school_world_history": {
+      "acc": true
+    },
+    "mmlu_human_aging": {
+      "acc": true
+    },
+    "mmlu_human_sexuality": {
+      "acc": true
+    },
+    "mmlu_humanities": {
+      "acc": true
+    },
+    "mmlu_international_law": {
+      "acc": true
+    },
+    "mmlu_jurisprudence": {
+      "acc": true
+    },
+    "mmlu_logical_fallacies": {
+      "acc": true
+    },
+    "mmlu_machine_learning": {
+      "acc": true
+    },
+    "mmlu_management": {
+      "acc": true
+    },
+    "mmlu_marketing": {
+      "acc": true
+    },
+    "mmlu_medical_genetics": {
+      "acc": true
+    },
+    "mmlu_miscellaneous": {
+      "acc": true
+    },
+    "mmlu_moral_disputes": {
+      "acc": true
+    },
+    "mmlu_moral_scenarios": {
+      "acc": true
+    },
+    "mmlu_nutrition": {
+      "acc": true
+    },
+    "mmlu_other": {
+      "acc": true
+    },
+    "mmlu_philosophy": {
+      "acc": true
+    },
+    "mmlu_prehistory": {
+      "acc": true
+    },
+    "mmlu_professional_accounting": {
+      "acc": true
+    },
+    "mmlu_professional_law": {
+      "acc": true
+    },
+    "mmlu_professional_medicine": {
+      "acc": true
+    },
+    "mmlu_professional_psychology": {
+      "acc": true
+    },
+    "mmlu_public_relations": {
+      "acc": true
+    },
+    "mmlu_security_studies": {
+      "acc": true
+    },
+    "mmlu_social_sciences": {
+      "acc": true
+    },
+    "mmlu_sociology": {
+      "acc": true
+    },
+    "mmlu_stem": {
+      "acc": true
+    },
+    "mmlu_us_foreign_policy": {
+      "acc": true
+    },
+    "mmlu_virology": {
+      "acc": true
+    },
+    "mmlu_world_religions": {
+      "acc": true
+    }
+  },
+  "n-samples": {
+    "mmlu_moral_scenarios": {
+      "original": 895,
+      "effective": 895
+    },
+    "mmlu_high_school_us_history": {
+      "original": 204,
+      "effective": 204
+    },
+    "mmlu_high_school_world_history": {
+      "original": 237,
+      "effective": 237
+    },
+    "mmlu_world_religions": {
+      "original": 171,
+      "effective": 171
+    },
+    "mmlu_formal_logic": {
+      "original": 126,
+      "effective": 126
+    },
+    "mmlu_moral_disputes": {
+      "original": 346,
+      "effective": 346
+    },
+    "mmlu_prehistory": {
+      "original": 324,
+      "effective": 324
+    },
+    "mmlu_international_law": {
+      "original": 121,
+      "effective": 121
+    },
+    "mmlu_logical_fallacies": {
+      "original": 163,
+      "effective": 163
+    },
+    "mmlu_professional_law": {
+      "original": 1534,
+      "effective": 1534
+    },
+    "mmlu_philosophy": {
+      "original": 311,
+      "effective": 311
+    },
+    "mmlu_high_school_european_history": {
+      "original": 165,
+      "effective": 165
+    },
+    "mmlu_jurisprudence": {
+      "original": 108,
+      "effective": 108
+    },
+    "mmlu_high_school_psychology": {
+      "original": 545,
+      "effective": 545
+    },
+    "mmlu_high_school_geography": {
+      "original": 198,
+      "effective": 198
+    },
+    "mmlu_high_school_macroeconomics": {
+      "original": 390,
+      "effective": 390
+    },
+    "mmlu_public_relations": {
+      "original": 110,
+      "effective": 110
+    },
+    "mmlu_security_studies": {
+      "original": 245,
+      "effective": 245
+    },
+    "mmlu_high_school_microeconomics": {
+      "original": 238,
+      "effective": 238
+    },
+    "mmlu_human_sexuality": {
+      "original": 131,
+      "effective": 131
+    },
+    "mmlu_sociology": {
+      "original": 201,
+      "effective": 201
+    },
+    "mmlu_professional_psychology": {
+      "original": 612,
+      "effective": 612
+    },
+    "mmlu_econometrics": {
+      "original": 114,
+      "effective": 114
+    },
+    "mmlu_us_foreign_policy": {
+      "original": 100,
+      "effective": 100
+    },
+    "mmlu_high_school_government_and_politics": {
+      "original": 193,
+      "effective": 193
+    },
+    "mmlu_marketing": {
+      "original": 234,
+      "effective": 234
+    },
+    "mmlu_professional_accounting": {
+      "original": 282,
+      "effective": 282
+    },
+    "mmlu_clinical_knowledge": {
+      "original": 265,
+      "effective": 265
+    },
+    "mmlu_college_medicine": {
+      "original": 173,
+      "effective": 173
+    },
+    "mmlu_miscellaneous": {
+      "original": 783,
+      "effective": 783
+    },
+    "mmlu_virology": {
+      "original": 166,
+      "effective": 166
+    },
+    "mmlu_business_ethics": {
+      "original": 100,
+      "effective": 100
+    },
+    "mmlu_professional_medicine": {
+      "original": 272,
+      "effective": 272
+    },
+    "mmlu_global_facts": {
+      "original": 100,
+      "effective": 100
+    },
+    "mmlu_nutrition": {
+      "original": 306,
+      "effective": 306
+    },
+    "mmlu_human_aging": {
+      "original": 223,
+      "effective": 223
+    },
+    "mmlu_management": {
+      "original": 103,
+      "effective": 103
+    },
+    "mmlu_medical_genetics": {
+      "original": 100,
+      "effective": 100
+    },
+    "mmlu_college_biology": {
+      "original": 144,
+      "effective": 144
+    },
+    "mmlu_high_school_computer_science": {
+      "original": 100,
+      "effective": 100
+    },
+    "mmlu_elementary_mathematics": {
+      "original": 378,
+      "effective": 378
+    },
+    "mmlu_astronomy": {
+      "original": 152,
+      "effective": 152
+    },
+    "mmlu_machine_learning": {
+      "original": 112,
+      "effective": 112
+    },
+    "mmlu_high_school_mathematics": {
+      "original": 270,
+      "effective": 270
+    },
+    "mmlu_electrical_engineering": {
+      "original": 145,
+      "effective": 145
+    },
+    "mmlu_college_chemistry": {
+      "original": 100,
+      "effective": 100
+    },
+    "mmlu_college_mathematics": {
+      "original": 100,
+      "effective": 100
+    },
+    "mmlu_high_school_statistics": {
+      "original": 216,
+      "effective": 216
+    },
+    "mmlu_high_school_biology": {
+      "original": 310,
+      "effective": 310
+    },
+    "mmlu_abstract_algebra": {
+      "original": 100,
+      "effective": 100
+    },
+    "mmlu_college_physics": {
+      "original": 102,
+      "effective": 102
+    },
+    "mmlu_conceptual_physics": {
+      "original": 235,
+      "effective": 235
+    },
+    "mmlu_computer_security": {
+      "original": 100,
+      "effective": 100
+    },
+    "mmlu_anatomy": {
+      "original": 135,
+      "effective": 135
+    },
+    "mmlu_college_computer_science": {
+      "original": 100,
+      "effective": 100
+    },
+    "mmlu_high_school_physics": {
+      "original": 151,
+      "effective": 151
+    },
+    "mmlu_high_school_chemistry": {
+      "original": 203,
+      "effective": 203
+    }
+  },
+  "config": {
+    "model": "hf",
+    "model_args": "pretrained=/home/migel/Tess-v2.5-qwen2-72B-safetensors,parallelize=True",
+    "model_num_parameters": 72706203648,
+    "model_dtype": "torch.float16",
+    "model_revision": "main",
+    "model_sha": "",
+    "batch_size": "8",
+    "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": "b3e4c49a",
+  "date": 1718167288.656124,
+  "pretty_env_info": "PyTorch version: 2.3.0+cu121\nIs debug build: False\nCUDA used to build PyTorch: 12.1\nROCM used to build PyTorch: N/A\n\nOS: Ubuntu 20.04.6 LTS (x86_64)\nGCC version: (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0\nClang version: Could not collect\nCMake version: version 3.29.3\nLibc version: glibc-2.31\n\nPython version: 3.10.14 (main, Apr  6 2024, 18:45:05) [GCC 9.4.0] (64-bit runtime)\nPython platform: Linux-5.15.0-1050-azure-x86_64-with-glibc2.31\nIs CUDA available: True\nCUDA runtime version: 12.1.105\nCUDA_MODULE_LOADING set to: LAZY\nGPU models and configuration: \nGPU 0: NVIDIA A100 80GB PCIe\nGPU 1: NVIDIA A100 80GB PCIe\nGPU 2: NVIDIA A100 80GB PCIe\nGPU 3: NVIDIA A100 80GB PCIe\n\nNvidia driver version: 530.30.02\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\nByte Order:                         Little Endian\nAddress sizes:                      48 bits physical, 48 bits virtual\nCPU(s):                             96\nOn-line CPU(s) list:                0-95\nThread(s) per core:                 1\nCore(s) per socket:                 48\nSocket(s):                          2\nNUMA node(s):                       4\nVendor ID:                          AuthenticAMD\nCPU family:                         25\nModel:                              1\nModel name:                         AMD EPYC 7V13 64-Core Processor\nStepping:                           1\nCPU MHz:                            2445.435\nBogoMIPS:                           4890.87\nHypervisor vendor:                  Microsoft\nVirtualization type:                full\nL1d cache:                          3 MiB\nL1i cache:                          3 MiB\nL2 cache:                           48 MiB\nL3 cache:                           384 MiB\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:             Not affected\nVulnerability Spec rstack overflow: Mitigation; safe RET, no microcode\nVulnerability Spec store bypass:    Vulnerable\nVulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2:           Mitigation; Retpolines, STIBP disabled, RSB filling, PBRSB-eIBRS Not affected\nVulnerability Srbds:                Not affected\nVulnerability Tsx async abort:      Not affected\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 pcid 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 invpcid_single vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves clzero xsaveerptr rdpru arat umip vaes vpclmulqdq rdpid fsrm\n\nVersions of relevant libraries:\n[pip3] numpy==1.26.4\n[pip3] torch==2.3.0\n[pip3] triton==2.3.0\n[conda] magma-cuda117             2.6.1                         1    pytorch\n[conda] mkl                       2022.2.1                 pypi_0    pypi\n[conda] mkl-include               2022.2.1                 pypi_0    pypi\n[conda] numpy                     1.24.4                   pypi_0    pypi\n[conda] pytorch-lightning         1.9.5                    pypi_0    pypi\n[conda] torch                     2.0.1                    pypi_0    pypi\n[conda] torch-nebula              0.16.10                  pypi_0    pypi\n[conda] torch-ort                 1.17.0                   pypi_0    pypi\n[conda] torchaudio                2.0.2+cu117              pypi_0    pypi\n[conda] torchdata                 0.6.1                    pypi_0    pypi\n[conda] torchmetrics              1.2.0                    pypi_0    pypi\n[conda] torchsnapshot             0.1.0                    pypi_0    pypi\n[conda] torchvision               0.15.2+cu117             pypi_0    pypi\n[conda] triton                    2.0.0                    pypi_0    pypi",
+  "transformers_version": "4.41.1",
+  "upper_git_hash": null,
+  "task_hashes": {},
+  "model_source": "hf",
+  "model_name": "/home/migel/Tess-v2.5-qwen2-72B-safetensors",
+  "model_name_sanitized": "__home__migel__Tess-v2.5-qwen2-72B-safetensors",
+  "system_instruction": null,
+  "system_instruction_sha": null,
+  "chat_template": null,
+  "chat_template_sha": null,
+  "start_time": 380863.826540975,
+  "end_time": 388726.503174757,
+  "total_evaluation_time_seconds": "7862.676633781986"
+}