{
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within XML tags:\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\\n\\nFor each function call, return a json object with function name and arguments within XML tags:\\n\\n{\\\"name\\\": , \\\"arguments\\\": }\\n<|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- content }}\n {{- '\\n' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}",
"chat_template_sha": "64f85b198065d0fba2a81f37e10ed68161ce2c19a754c7100e67e0ca2ee9c326",
"config": {
"batch_size": "32",
"batch_sizes": [],
"bootstrap_iters": 100000,
"device": "cuda:0",
"fewshot_seed": 1234,
"gen_kwargs": {},
"limit": null,
"model": "hf",
"model_args": "pretrained=Qwen/Qwen3-4B-Instruct-2507",
"model_dtype": "torch.bfloat16",
"model_num_parameters": 4022468096,
"model_revision": "main",
"model_sha": "cdbee75f17c01a7cc42f958dc650907174af0554",
"numpy_seed": 1234,
"random_seed": 0,
"torch_seed": 1234,
"use_cache": "[redacted]"
},
"configs": {
"gsm8k": {
"dataset_name": "main",
"dataset_path": "openai/gsm8k",
"description": "",
"doc_to_target": "{{answer}}",
"doc_to_text": "Question: {{question}}\nAnswer:",
"fewshot_config": {
"doc_to_choice": null,
"doc_to_target": "{{answer}}",
"doc_to_text": "Question: {{question}}\nAnswer:",
"fewshot_delimiter": "\n\n",
"fewshot_indices": null,
"gen_prefix": null,
"process_docs": null,
"sampler": "default",
"samples": null,
"split": "train",
"target_delimiter": " "
},
"fewshot_delimiter": "\n\n",
"fewshot_split": "train",
"filter_list": [
{
"filter": [
{
"function": "regex",
"regex_pattern": "#### (\\-?[0-9\\.\\,]+)"
},
{
"function": "take_first"
}
],
"name": "strict-match"
},
{
"filter": [
{
"function": "regex",
"group_select": -1,
"regex_pattern": "(-?[$0-9.,]{2,})|(-?[0-9]+)"
},
{
"function": "take_first"
}
],
"name": "flexible-extract"
}
],
"generation_kwargs": {
"do_sample": false,
"temperature": 0.0,
"until": [
"Question:",
"",
"<|im_end|>"
]
},
"metadata": {
"config_source": "[redacted]",
"dtype": "bfloat16",
"pretrained": "Qwen/Qwen3-4B-Instruct-2507",
"trust_remote_code": true,
"version": 3.0
},
"metric_list": [
{
"aggregation": "mean",
"higher_is_better": true,
"ignore_case": true,
"ignore_punctuation": false,
"metric": "exact_match",
"regexes_to_ignore": [
",",
"\\$",
"(?s).*#### ",
"\\.$"
]
}
],
"num_fewshot": 5,
"output_type": "generate_until",
"repeats": 1,
"should_decontaminate": false,
"target_delimiter": " ",
"task": "gsm8k",
"test_split": "test",
"training_split": "train",
"unsafe_code": false
}
},
"date": 1780942857.9108624,
"eot_token_id": 151645,
"fewshot_as_multiturn": true,
"git_hash": null,
"group_subtasks": {},
"higher_is_better": {
"gsm8k": {
"exact_match": true
}
},
"lm_eval_version": "0.4.12",
"max_length": 262144,
"model_name": "Qwen/Qwen3-4B-Instruct-2507",
"model_name_sanitized": "Qwen/Qwen3-4B-Instruct-2507",
"model_source": "Qwen/Qwen3-4B-Instruct-2507",
"n-samples": {
"gsm8k": {
"effective": 1319,
"original": 1319
}
},
"n-shot": {
"gsm8k": 5
},
"results": {
"gsm8k": {
"alias": "gsm8k",
"exact_match,flexible-extract": 0.7915087187263078,
"exact_match,strict-match": 0.7323730098559514,
"exact_match_stderr,flexible-extract": 0.01118958798579141,
"exact_match_stderr,strict-match": 0.012194764427053348,
"name": "gsm8k",
"sample_len": 1319
}
},
"system_instruction": null,
"system_instruction_sha": null,
"task_hashes": {
"gsm8k": "57f6f099e46d41808275113fe524b6af081154f7c87fa7826e3dd1775f468206"
},
"tokenizer_bos_token": [
null,
"None"
],
"tokenizer_eos_token": [
"<|im_end|>",
"151645"
],
"tokenizer_pad_token": [
"<|endoftext|>",
"151643"
],
"total_evaluation_time_seconds": "1433.1546569541097",
"transformers_version": "4.57.6",
"upper_git_hash": null,
"versions": {
"gsm8k": 3.0
}
}