I’m trying to fine tune gpt-4o-mini-2024-07-18 model. I’m getting an error in my json-line format.
I’m not sure how to use strict in fine-tuning but couldn’t find much resources or examples.
This is the format:
messages_list =
{
'messages':
[
{'role': 'system', 'content': prompt},
{'role': 'user', 'content': question},
{'role': 'assistant', 'tool_calls':
[
{
'id': 'call_id',
'type': 'function',
'function': {
'name': function_name,
'arguments': params_str
}
}
]
},
{'role': 'tool', 'tool_call_id': 'call_id', 'content': toolResponse},
{'role': 'assistant', 'content': answer}
],
'tools':
[
{
'type': 'function',
'function':
{
'name': function_name,
'description': function_description,
'parameters':
{
'type': 'object',
'properties': properties,
'required': required_params,
'additionalProperties': False,
},
'strict': True,
}
}
]
}
Note: it is working perfectly without strict and additionalProperties