[Fix] Optimize the evaluation process for OCR-Reasoning

[shannanyinxiang]

fix1: delete the hardcoded "nproc=1" in the evaluation of OCR_Reasoning

Delete the hardcoded "nproc=1" in the evaluation of OCR_Reasoning to accelerate the LLM judging process.

fix2: Increase max_tokens of the LLM Judge for OCR-Reasoning

The OCR-Reasoning evaluation involves scoring of reasoning processes where the LLM judge is prompted to output explanatory text before final ratings.

VLMEvalKit/vlmeval/dataset/utils/ocr_reasoning.py

Line 7 in 2c25371

judge_prompts = '''Please act as an impartial judge and evaluate the quality of the response provided by an AI assistant to the user question displayed below. Your evaluation should consider correctness and helpfulness. You will be given a reference answer and the assistant's answer. Begin your evaluation by comparing the assistant's answer with the reference answer. Identify and correct any mistakes. Be as objective as possible. After providing your explanation, you must rate the response on a scale of 1 to 10 by strictly following this format: \"[[rating]]\", for example: \"Rating: [[5]]\".\n\n[Question]\n{question}\n\n[The Start of Reference Answer]\n{ref_answer_1}\n[The End of Reference Answer]\n\n[The Start of Assistant's Answer]\n{answer}\n[The End of Assistant's Answer]". Again, you must output a score by strictly following this format: \"[[rating]]\", for example: \"Rating: [[5]]\".''' # noqa e501

Therefore, the original 1024 max_tokens setting is insufficient, constantly leading to unintended response truncation.