`small_model_filename` cannot be assigned during fine-tuning

The below code

https://github.com/anarchy-ai/LLM-VM/blob/7a5877b6adb2a71892203a71ac2095a01357bb1b/src/llm_vm/completion/optimize.py#L261

tries to extract `small_model_filename` from `kwargs` which is passed down from `client.complete(...)` -> `optimizer.complete(...)` -> `optimizer.complete_delay_train(...)`

I think the main purpose of this is to make sure we can save finetuned model to any location via ` llm_vm.client`, but it will cause error because the same `kwargs` with `small_model_filename` will be passed to chat_gpt model:

https://github.com/anarchy-ai/LLM-VM/blob/7a5877b6adb2a71892203a71ac2095a01357bb1b/src/llm_vm/completion/optimize.py#L254

Resulting in

```
openai.error.InvalidRequestError: Unrecognized request argument supplied: small_model_filename
```