File size: 7,116 Bytes
40bc205 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 | {
"results": {
"hellaswag": {
"name": "hellaswag",
"alias": "hellaswag",
"sample_len": 100,
"acc,none": 0.51,
"acc_stderr,none": 0.05024183937956913,
"acc_norm,none": 0.68,
"acc_norm_stderr,none": 0.046882617226215076
},
"arc_easy": {
"name": "arc_easy",
"alias": "arc_easy",
"sample_len": 100,
"acc,none": 0.8,
"acc_stderr,none": 0.04020151261036849,
"acc_norm,none": 0.81,
"acc_norm_stderr,none": 0.039427724440366255
}
},
"group_subtasks": {},
"configs": {
"arc_easy": {
"task": "arc_easy",
"dataset_path": "allenai/ai2_arc",
"dataset_name": "ARC-Easy",
"training_split": "train",
"validation_split": "validation",
"test_split": "test",
"doc_to_text": "Question: {{question}}\nAnswer:",
"doc_to_target": "{{choices.label.index(answerKey)}}",
"unsafe_code": false,
"doc_to_choice": "{{choices.text}}",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "default",
"split": null,
"process_docs": null,
"fewshot_indices": null,
"samples": null,
"doc_to_text": "Question: {{question}}\nAnswer:",
"doc_to_choice": "{{choices.text}}",
"doc_to_target": "{{choices.label.index(answerKey)}}",
"gen_prefix": null,
"fewshot_delimiter": "\n\n",
"target_delimiter": " "
},
"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": true,
"doc_to_decontamination_query": "Question: {{question}}\nAnswer:",
"metadata": {
"version": 1.0,
"pretrained": "models/Qwen/Qwen3.5-4B",
"dtype": "bfloat16",
"config_source": "/Volumes/외장디스크1/오픈소스 모델/research/qwen35-moe-a3b/.venv-eval/lib/python3.14/site-packages/lm_eval/tasks/arc/arc_easy.yaml"
}
},
"hellaswag": {
"task": "hellaswag",
"dataset_path": "Rowan/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}}",
"unsafe_code": false,
"doc_to_choice": "choices",
"description": "",
"target_delimiter": " ",
"fewshot_delimiter": "\n\n",
"fewshot_config": {
"sampler": "default",
"split": null,
"process_docs": "<function process_docs at 0x13ebcfd70>",
"fewshot_indices": null,
"samples": null,
"doc_to_text": "{{query}}",
"doc_to_choice": "choices",
"doc_to_target": "{{label}}",
"gen_prefix": null,
"fewshot_delimiter": "\n\n",
"target_delimiter": " "
},
"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,
"pretrained": "models/Qwen/Qwen3.5-4B",
"dtype": "bfloat16",
"config_source": "/Volumes/외장디스크1/오픈소스 모델/research/qwen35-moe-a3b/.venv-eval/lib/python3.14/site-packages/lm_eval/tasks/hellaswag/hellaswag.yaml"
}
}
},
"versions": {
"arc_easy": 1.0,
"hellaswag": 1.0
},
"n-shot": {
"arc_easy": 0,
"hellaswag": 0
},
"higher_is_better": {
"arc_easy": {
"acc": true,
"acc_norm": true
},
"hellaswag": {
"acc": true,
"acc_norm": true
}
},
"n-samples": {
"hellaswag": {
"original": 10042,
"effective": 100
},
"arc_easy": {
"original": 2376,
"effective": 100
}
},
"config": {
"model": "hf",
"model_args": {
"pretrained": "models/Qwen/Qwen3.5-4B",
"dtype": "bfloat16"
},
"model_num_parameters": 4205751296,
"model_dtype": "torch.bfloat16",
"model_revision": "main",
"model_sha": "",
"batch_size": "1",
"batch_sizes": [],
"device": "mps",
"use_cache": null,
"limit": 100.0,
"bootstrap_iters": 100000,
"gen_kwargs": {},
"random_seed": 0,
"numpy_seed": 1234,
"torch_seed": 1234,
"fewshot_seed": 1234
},
"git_hash": null,
"date": 1787550063.559031,
"pretty_env_info": "PyTorch version: 2.11.0\nIs debug build: False\nCUDA used to build PyTorch: None\nROCM used to build PyTorch: N/A\n\nOS: macOS 26.4.1 (arm64)\nGCC version: Could not collect\nClang version: 21.0.0 (clang-2100.0.123.102)\nCMake version: version 4.4.0\nLibc version: N/A\n\nPython version: 3.14.6 (main, Jun 10 2026, 10:03:53) [Clang 21.0.0 (clang-2100.0.123.102)] (64-bit runtime)\nPython platform: macOS-26.4.1-arm64-arm-64bit-Mach-O\nIs CUDA available: False\nCUDA runtime version: No CUDA\nCUDA_MODULE_LOADING set to: N/A\nGPU models and configuration: No CUDA\nNvidia driver version: No CUDA\ncuDNN version: No CUDA\nIs XPU available: False\nHIP runtime version: N/A\nMIOpen runtime version: N/A\nIs XNNPACK available: True\nCaching allocator config: N/A\n\nCPU:\nApple M4\n\nVersions of relevant libraries:\n[pip3] numpy==2.4.4\n[pip3] torch==2.11.0\n[conda] Could not collect",
"transformers_version": "5.13.0",
"lm_eval_version": "0.4.12",
"upper_git_hash": null,
"tokenizer_pad_token": [
"<|endoftext|>",
"248044"
],
"tokenizer_eos_token": [
"<|im_end|>",
"248046"
],
"tokenizer_bos_token": [
null,
"None"
],
"eot_token_id": 248046,
"max_length": 262144,
"task_hashes": {
"hellaswag": "4f7d86a1e256013e93651a0d8510973180c5f31142ca184d9677955a29676af1",
"arc_easy": "fd3a493579cfdccf229a32d7c26710006fc4edf7c024add74f70c416c6dab3ce"
},
"model_source": "hf",
"model_name": "models/Qwen/Qwen3.5-4B",
"model_name_sanitized": "models__Qwen__Qwen3.5-4B",
"system_instruction": null,
"system_instruction_sha": null,
"fewshot_as_multiturn": null,
"chat_template": null,
"chat_template_sha": null,
"total_evaluation_time_seconds": "257.4533243330079"
} |