Merge pull request #23 from QwenLM/add_chat_eval

add evaluation code for Qwen-7B-Chat

eval/evaluate_chat_ceval.py

@@ -0,0 +1,290 @@
+import os
+import pandas as pd
+import numpy as np
+import argparse
+import datasets
+import torch
+import re
+from thefuzz import process
+from typing import List
+from tqdm import tqdm
+from transformers.trainer_utils import set_seed
+
+'''
+wget https://huggingface.co/datasets/ceval/ceval-exam/resolve/main/ceval-exam.zip
+mkdir data/ceval
+mv ceval-exam.zip data/ceval
+cd data/ceval; unzip ceval-exam.zip
+cd ../../
+
+pip install thefuzz
+python eval/evaluate_chat_ceval.py -d data/ceval
+'''
+
+def load_models_tokenizer(args):
+    from transformers import AutoModelForCausalLM, AutoTokenizer
+    from transformers.generation import GenerationConfig
+
+    tokenizer = AutoTokenizer.from_pretrained(args.checkpoint_path, trust_remote_code=True)
+    model = AutoModelForCausalLM.from_pretrained(args.checkpoint_path, device_map="auto", trust_remote_code=True, bf16=True, use_flash_attn=True).eval()
+    model.generation_config = GenerationConfig.from_pretrained(args.checkpoint_path, trust_remote_code=True)
+    model.generation_config.do_sample = False # use greedy decoding
+    return model, tokenizer
+
+def process_before_extraction(gen, question, choice_dict):
+    # Example Prompt:
+    # 关于传输层的面向连接服务的特性是____。
+    # A. 既不保证可靠，也不保证按序交付
+    # B. 不保证可靠，但保证按序交付
+    # C. 保证可靠，但不保证按序交付
+    # D. 既保证可靠，也保证按序交付
+    # Example Model Output：
+    # 关于传输层的面向连接服务的特性是既保证可靠，也保证按序交付
+    # Processed Output:
+    # 答案是D
+
+    question_split = question.rstrip("。").split("。")[-1].split("_")
+
+    # replacing the question
+    if len(question_split[0].strip()) > 4:
+        gen = gen.replace(question_split[0], "答案是")
+    if len(question_split[-1].strip()) > 4:
+        gen = gen.replace(question_split[-1], "")
+
+    # replace the choice by letter in the generated sentence
+    # from longest one to shortest one
+    for key, val in sorted(choice_dict.items(), key=lambda x: len(x[1]), reverse=True):
+        gen = gen.replace(val.rstrip("。"), key)
+    return gen
+
+def count_substr(gen, pattern):
+    return len(re.findall(pattern, gen))
+
+def extract_choice(gen, prompt, choice_list):
+    # 答案是A | 选项是A | 应该选A选项
+    res = re.search(r"(?:(?:选|选择|选定)|(?:(?:答案|选项)(?![^ABCD]{0,10}?(?:不|非)[^ABCD]{0,10}?(?:是|为|：|:|】))[^ABCD]{0,10}?(?:是|为|：|:|】))[^ABCD]{0,10}?)(A|B|C|D)(?:选项)?(?:\)|。|\.|，|,|．|、|A|B|C|D|$)", gen)
+        
+    # A选项正确 | A选项符合题意
+    if res is None:
+        res = re.search(r"(A|B|C|D)(?:选?项)?(?![^ABCD]{0,4}?(?:不|非)[^ABCD]{0,4}?(?:正确|对|符合))[^ABCD]{0,4}?(?:正确|对|符合)", gen)        
+
+    # 直接输出 A
+    if res is None:
+        res = re.search(r"^(A|B|C|D)(?:。|\.|，|,|．|$)", gen)
+
+    # 获取第一个出现的字母
+    if res is None:
+        res = re.search(r"(?<![a-zA-Z])(A|B|C|D)(?![a-zA-Z=])", gen)
+
+    if res is None:
+        return choices[choice_list.index(process.extractOne(gen, choice_list)[0])]
+    else:
+        return res.group(1)
+
+def format_example(line):
+    example = line['question'] + "\n\n"
+    for choice in choices:
+        example += f'{choice}. {line[f"{choice}"]}\n' 
+    return example
+
+def extract_answer(response, row):
+    prompt = row['question']
+    gen = process_before_extraction(response, prompt, {choice: row[choice] for choice in choices})
+    if not isinstance(prompt, str):
+        prompt = prompt[0]
+    pred = extract_choice(gen, prompt, [row[choice] for choice in choices])
+    return pred
+
+@torch.no_grad()
+def eval_subject(
+        model,
+        tokenizer,
+        subject_name,
+        test_df,
+        save_result_dir=None,
+        overwrite=False,
+        **kwargs
+):
+
+    result_path = os.path.join(save_result_dir, f'{subject_name}_result.csv')
+    if not overwrite and os.path.exists(result_path):
+        print(f"{result_path} existed, skip!")
+        score = []
+        for (_, datarow), (_, resultrow) in zip(test_df.iterrows(), pd.read_csv(result_path).iterrows()):
+            pred = extract_answer(resultrow['model_response'], datarow)
+            correct = 1 if pred == datarow['answer'] else 0
+            score.append(correct)
+        correct_ratio = 100 * sum(score) / len(score)
+        return correct_ratio
+
+    responses = []
+    result = []
+    score = []
+
+    for _, row in tqdm(test_df.iterrows(), total=len(test_df)):
+        question = format_example(row)
+
+        response, history = model.chat(
+            tokenizer,
+            question,
+            history=None,
+        )
+        print(question)
+        print(response)
+        pred = extract_answer(response, row)
+        print(pred)
+        print("======================")
+        
+        if 'answer' in row:
+            correct = 1 if pred == row['answer'] else 0
+            score.append(correct)
+            if args.debug: print(f'{question} pred: {pred} ref: {row["answer"]}')
+        responses.append(response)
+        result.append(pred)
+
+    if score:
+        correct_ratio = 100 * sum(score) / len(score)
+        if args.debug: print(subject_name, correct_ratio)
+    else:
+        correct_ratio = 0
+    if save_result_dir:
+        test_df['model_response'] = responses
+        test_df['model_output'] = result
+        if score:
+            test_df["correctness"] = score
+        os.makedirs(save_result_dir, exist_ok=True)
+        test_df.to_csv(result_path, encoding="utf-8", index=False)
+
+    return correct_ratio
+
+
+def cal_ceval(res):
+    acc_sum_dict = dict()
+    acc_norm_sum_dict = dict()
+    cnt_dict = dict()
+    acc_sum = 0.
+    cnt = 0
+    hard_cnt = 0
+    hard_acc_sum = 0.
+    for tt in res.keys():
+        name = tt.split('-')[-1]
+        acc_sum += float(res[tt])
+        cnt += 1
+        class_ = TASK_NAME_MAPPING[name][2]
+        if class_ not in acc_sum_dict:
+            acc_sum_dict[class_] = 0.
+            acc_norm_sum_dict[class_] = 0.
+            cnt_dict[class_] = 0.
+        if name in hard_list:
+            hard_cnt += 1
+            hard_acc_sum += float(res[tt])
+        acc_sum_dict[class_] += float(res[tt])
+        cnt_dict[class_] += 1
+    print('\n\n\n')
+    for k in ['STEM', 'Social Science', 'Humanities', 'Other']:
+        if k in cnt_dict:
+            print('%s acc: %.2f ' % (
+                k, acc_sum_dict[k] / cnt_dict[k]))
+    if hard_cnt > 0:
+        print('Hard acc:%.2f ' % (hard_acc_sum / hard_cnt))
+    print('AVERAGE acc:%.2f ' % (acc_sum / cnt))
+
+
+TASK_NAME_MAPPING = {
+    "computer_network": ["Computer Network", "\u8ba1\u7b97\u673a\u7f51\u7edc", "STEM"],
+    "operating_system": ["Operating System", "\u64cd\u4f5c\u7cfb\u7edf", "STEM"],
+    "computer_architecture": ["Computer Architecture", "\u8ba1\u7b97\u673a\u7ec4\u6210", "STEM"],
+    "college_programming": ["College Programming", "\u5927\u5b66\u7f16\u7a0b", "STEM"],
+    "college_physics": ["College Physics", "\u5927\u5b66\u7269\u7406", "STEM"],
+    "college_chemistry": ["College Chemistry", "\u5927\u5b66\u5316\u5b66", "STEM"],
+    "advanced_mathematics": ["Advanced Mathematics", "\u9ad8\u7b49\u6570\u5b66", "STEM"],
+    "probability_and_statistics": ["Probability and Statistics", "\u6982\u7387\u7edf\u8ba1", "STEM"],
+    "discrete_mathematics": ["Discrete Mathematics", "\u79bb\u6563\u6570\u5b66", "STEM"],
+    "electrical_engineer": ["Electrical Engineer", "\u6ce8\u518c\u7535\u6c14\u5de5\u7a0b\u5e08", "STEM"],
+    "metrology_engineer": ["Metrology Engineer", "\u6ce8\u518c\u8ba1\u91cf\u5e08", "STEM"],
+    "high_school_mathematics": ["High School Mathematics", "\u9ad8\u4e2d\u6570\u5b66", "STEM"],
+    "high_school_physics": ["High School Physics", "\u9ad8\u4e2d\u7269\u7406", "STEM"],
+    "high_school_chemistry": ["High School Chemistry", "\u9ad8\u4e2d\u5316\u5b66", "STEM"],
+    "high_school_biology": ["High School Biology", "\u9ad8\u4e2d\u751f\u7269", "STEM"],
+    "middle_school_mathematics": ["Middle School Mathematics", "\u521d\u4e2d\u6570\u5b66", "STEM"],
+    "middle_school_biology": ["Middle School Biology", "\u521d\u4e2d\u751f\u7269", "STEM"],
+    "middle_school_physics": ["Middle School Physics", "\u521d\u4e2d\u7269\u7406", "STEM"],
+    "middle_school_chemistry": ["Middle School Chemistry", "\u521d\u4e2d\u5316\u5b66", "STEM"],
+    "veterinary_medicine": ["Veterinary Medicine", "\u517d\u533b\u5b66", "STEM"],
+    "college_economics": ["College Economics", "\u5927\u5b66\u7ecf\u6d4e\u5b66", "Social Science"],
+    "business_administration": ["Business Administration", "\u5de5\u5546\u7ba1\u7406", "Social Science"],
+    "marxism": ["Marxism", "\u9a6c\u514b\u601d\u4e3b\u4e49\u57fa\u672c\u539f\u7406", "Social Science"],
+    "mao_zedong_thought": ["Mao Zedong Thought", "\u6bdb\u6cfd\u4e1c\u601d\u60f3\u548c\u4e2d\u56fd\u7279\u8272\u793e\u4f1a\u4e3b\u4e49\u7406\u8bba\u4f53\u7cfb\u6982\u8bba", "Social Science"],
+    "education_science": ["Education Science", "\u6559\u80b2\u5b66", "Social Science"],
+    "teacher_qualification": ["Teacher Qualification", "\u6559\u5e08\u8d44\u683c", "Social Science"],
+    "high_school_politics": ["High School Politics", "\u9ad8\u4e2d\u653f\u6cbb", "Social Science"],
+    "high_school_geography": ["High School Geography", "\u9ad8\u4e2d\u5730\u7406", "Social Science"],
+    "middle_school_politics": ["Middle School Politics", "\u521d\u4e2d\u653f\u6cbb", "Social Science"],
+    "middle_school_geography": ["Middle School Geography", "\u521d\u4e2d\u5730\u7406", "Social Science"],
+    "modern_chinese_history": ["Modern Chinese History", "\u8fd1\u4ee3\u53f2\u7eb2\u8981", "Humanities"],
+    "ideological_and_moral_cultivation": ["Ideological and Moral Cultivation", "\u601d\u60f3\u9053\u5fb7\u4fee\u517b\u4e0e\u6cd5\u5f8b\u57fa\u7840", "Humanities"],
+    "logic": ["Logic", "\u903b\u8f91\u5b66", "Humanities"],
+    "law": ["Law", "\u6cd5\u5b66", "Humanities"],
+    "chinese_language_and_literature": ["Chinese Language and Literature", "\u4e2d\u56fd\u8bed\u8a00\u6587\u5b66", "Humanities"],
+    "art_studies": ["Art Studies", "\u827a\u672f\u5b66", "Humanities"],
+    "professional_tour_guide": ["Professional Tour Guide", "\u5bfc\u6e38\u8d44\u683c", "Humanities"],
+    "legal_professional": ["Legal Professional", "\u6cd5\u5f8b\u804c\u4e1a\u8d44\u683c", "Humanities"],
+    "high_school_chinese": ["High School Chinese", "\u9ad8\u4e2d\u8bed\u6587", "Humanities"],
+    "high_school_history": ["High School History", "\u9ad8\u4e2d\u5386\u53f2", "Humanities"],
+    "middle_school_history": ["Middle School History", "\u521d\u4e2d\u5386\u53f2", "Humanities"],
+    "civil_servant": ["Civil Servant", "\u516c\u52a1\u5458", "Other"],
+    "sports_science": ["Sports Science", "\u4f53\u80b2\u5b66", "Other"],
+    "plant_protection": ["Plant Protection", "\u690d\u7269\u4fdd\u62a4", "Other"],
+    "basic_medicine": ["Basic Medicine", "\u57fa\u7840\u533b\u5b66", "Other"],
+    "clinical_medicine": ["Clinical Medicine", "\u4e34\u5e8a\u533b\u5b66", "Other"],
+    "urban_and_rural_planner": ["Urban and Rural Planner", "\u6ce8\u518c\u57ce\u4e61\u89c4\u5212\u5e08", "Other"],
+    "accountant": ["Accountant", "\u6ce8\u518c\u4f1a\u8ba1\u5e08", "Other"],
+    "fire_engineer": ["Fire Engineer", "\u6ce8\u518c\u6d88\u9632\u5de5\u7a0b\u5e08", "Other"],
+    "environmental_impact_assessment_engineer": ["Environmental Impact Assessment Engineer", "\u73af\u5883\u5f71\u54cd\u8bc4\u4ef7\u5de5\u7a0b\u5e08", "Other"],
+    "tax_accountant": ["Tax Accountant", "\u7a0e\u52a1\u5e08", "Other"],
+    "physician": ["Physician", "\u533b\u5e08\u8d44\u683c", "Other"]
+}
+hard_list = ['advanced_mathematics', 'discrete_mathematics', 'probability_and_statistics', 'college_physics', 'college_chemistry', 'high_school_mathematics', 'high_school_physics', 'high_school_chemistry']
+choices = ["A", "B", "C", "D"]
+
+
+def main(args):
+    print("loading model weights")
+    if args.checkpoint_path:
+        model, tokenizer = load_models_tokenizer(args)
+    else:
+        model, tokenizer = None, None
+    print("model loaded")
+    dev_result = {}
+    for subject_name in tqdm(TASK_NAME_MAPPING.keys()):
+        val_file_path = os.path.join(args.eval_data_path, 'val', f'{subject_name}_val.csv')
+        # dev_file_path = os.path.join(args.eval_data_path, 'dev', f'{subject_name}_dev.csv')
+        # test_file_path = os.path.join(args.eval_data_path, 'test', f'{subject_name}_test.csv')
+        val_df = pd.read_csv(val_file_path)
+        # dev_df = pd.read_csv(dev_file_path)
+        # test_df = pd.read_csv(test_file_path) 
+
+        score = eval_subject(model, tokenizer, subject_name, val_df,
+                             save_result_dir=f"outs_chat/ceval_eval_result", overwrite=args.overwrite)
+        dev_result[subject_name] = score
+    cal_ceval(dev_result)
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser(description='Test HF checkpoint.')
+    parser.add_argument('-c', '--checkpoint-path', type=str, help='Checkpoint path', default="Qwen/Qwen-7B-Chat")
+    parser.add_argument('-s', '--seed', type=int, default=1234, help='Random seed')
+
+    """Provide extra arguments required for tasks."""
+    group = parser.add_argument_group(title='Evaluation options')
+    group.add_argument('-d', '--eval_data_path', type=str, required=True,
+                       help='Path to eval data')
+    group.add_argument("--debug", action='store_true', default=False,
+                       help='Print infos.')
+    group.add_argument("--overwrite", action='store_true', default=False,
+                       help='Overwrite existed results')
+
+    args = parser.parse_args()
+    set_seed(args.seed)
+
+    main(args)

eval/evaluate_chat_gsm8k.py

@@ -0,0 +1,137 @@
+import random
+import tqdm
+import os
+import re
+import sys
+import torch
+import numpy as np
+import jsonlines
+import argparse
+import json
+from pathlib import Path
+from datasets import load_from_disk,load_dataset
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers.generation import GenerationConfig
+
+'''
+python eval/evaluate_chat_gsm8k.py [--use-fewshot]
+'''
+
+INVALID_ANS = "[invalid]"
+DEVICE  = "cuda:0"
+
+def doc_to_text(doc, use_fewshot):
+    if use_fewshot:
+        context = "Question: Angelo and Melanie want to plan how many hours over the next week they should study together for their test next week. They have 2 chapters of their textbook to study and 4 worksheets to memorize. They figure out that they should dedicate 3 hours to each chapter of their textbook and 1.5 hours for each worksheet. If they plan to study no more than 4 hours each day, how many days should they plan to study total over the next week if they take a 10-minute break every hour, include 3 10-minute snack breaks each day, and 30 minutes for lunch each day?\nLet's think step by step\n" \
+                "Angelo and Melanie think they should dedicate 3 hours to each of the 2 chapters, 3 hours x 2 chapters = 6 hours total.\nFor the worksheets they plan to dedicate 1.5 hours for each worksheet, 1.5 hours x 4 worksheets = 6 hours total.\nAngelo and Melanie need to start with planning 12 hours to study, at 4 hours a day, 12 / 4 = 3 days.\nHowever, they need to include time for breaks and lunch. Every hour they want to include a 10-minute break, so 12 total hours x 10 minutes = 120 extra minutes for breaks.\nThey also want to include 3 10-minute snack breaks, 3 x 10 minutes = 30 minutes.\nAnd they want to include 30 minutes for lunch each day, so 120 minutes for breaks + 30 minutes for snack breaks + 30 minutes for lunch = 180 minutes, or 180 / 60 minutes per hour = 3 extra hours.\nSo Angelo and Melanie want to plan 12 hours to study + 3 hours of breaks = 15 hours total.\nThey want to study no more than 4 hours each day, 15 hours / 4 hours each day = 3.75\nThey will need to plan to study 4 days to allow for all the time they need.\nThe answer is 4\n\n" \
+                "Question: Mark's basketball team scores 25 2 pointers, 8 3 pointers and 10 free throws.  Their opponents score double the 2 pointers but half the 3 pointers and free throws.  What's the total number of points scored by both teams added together?\nLet's think step by step\n" \
+                "Mark's team scores 25 2 pointers, meaning they scored 25*2= 50 points in 2 pointers.\nHis team also scores 6 3 pointers, meaning they scored 8*3= 24 points in 3 pointers\nThey scored 10 free throws, and free throws count as one point so they scored 10*1=10 points in free throws.\nAll together his team scored 50+24+10= 84 points\nMark's opponents scored double his team's number of 2 pointers, meaning they scored 50*2=100 points in 2 pointers.\nHis opponents scored half his team's number of 3 pointers, meaning they scored 24/2= 12 points in 3 pointers.\nThey also scored half Mark's team's points in free throws, meaning they scored 10/2=5 points in free throws.\nAll together Mark's opponents scored 100+12+5=117 points\nThe total score for the game is both team's scores added together, so it is 84+117=201 points\nThe answer is 201\n\n" \
+                "Question: Bella has two times as many marbles as frisbees. She also has 20 more frisbees than deck cards. If she buys 2/5 times more of each item, what would be the total number of the items she will have if she currently has 60 marbles?\nLet's think step by step\n" \
+                "When Bella buys 2/5 times more marbles, she'll have increased the number of marbles by 2/5*60 = 24\nThe total number of marbles she'll have is 60+24 = 84\nIf Bella currently has 60 marbles, and she has two times as many marbles as frisbees, she has 60/2 = 30 frisbees.\nIf Bella buys 2/5 times more frisbees, she'll have 2/5*30 = 12 more frisbees.\nThe total number of frisbees she'll have will increase to 30+12 = 42\nBella also has 20 more frisbees than deck cards, meaning she has 30-20 = 10 deck cards\nIf she buys 2/5 times more deck cards, she'll have 2/5*10 = 4 more deck cards.\nThe total number of deck cards she'll have is 10+4 = 14\nTogether, Bella will have a total of 14+42+84 = 140 items\nThe answer is 140\n\n" \
+                "Question: A group of 4 fruit baskets contains 9 apples, 15 oranges, and 14 bananas in the first three baskets and 2 less of each fruit in the fourth basket. How many fruits are there?\nLet's think step by step\n" \
+                "For the first three baskets, the number of apples and oranges in one basket is 9+15=24\nIn total, together with bananas, the number of fruits in one basket is 24+14=38 for the first three baskets.\nSince there are three baskets each having 38 fruits, there are 3*38=114 fruits in the first three baskets.\nThe number of apples in the fourth basket is 9-2=7\nThere are also 15-2=13 oranges in the fourth basket\nThe combined number of oranges and apples in the fourth basket is 13+7=20\nThe fourth basket also contains 14-2=12 bananas.\nIn total, the fourth basket has 20+12=32 fruits.\nThe four baskets together have 32+114=146 fruits.\nThe answer is 146\n\n" \
+                f"Question: {doc['question']}\nLet's think step by step"
+    else:
+        context = doc['question']
+    return context
+
+def decode(tokens_list, tokenizer, raw_text_len):
+    sents = []
+    # print(len(tokens_list))
+    for tokens in tokens_list:
+        tokens = tokens.cpu().numpy().tolist()
+        sent = tokenizer.tokenizer.decode(
+            tokens[raw_text_len:])
+        sent = sent.split('<|endoftext|>')[0]
+        sent = sent.split('\n\n\n')[0]
+        sent = sent.split("\n\n")[0]
+        sent = sent.split("Question:")[0]
+        sents.append(sent)
+    return sents
+
+def generate_sample(model, tokenizer, question):
+    response, history = model.chat(
+        tokenizer,
+        question,
+        history=None,
+    )
+    print(question)
+    print("-------------")
+    print(response)
+    print("=============")
+    return response
+
+
+def extract_answer_hf(completion):
+    def _get_last_digit(s):
+        _PAT_LAST_DIGIT = re.compile(r"(?<=(\s|[\$%#{]))([+-])?(?=(\S))(0|([1-9](\d*|\d{0,2}(,\d{3})*)))?(\.\d*[1-9])?(?=(\s|[.,}]|$))")
+        match = list(_PAT_LAST_DIGIT.finditer(s))
+        if match:
+            last_digit = match[-1].group().replace(",", "").replace("+", "")
+            # print(f"The last digit in {s} is {last_digit}")
+        else:
+            last_digit = None
+            print(f"No digits found in {s!r}")
+        return last_digit
+
+    job_gen = completion.strip('.').replace('\n', '\\n')
+    last_digit = _get_last_digit(job_gen)
+    if last_digit is not None:
+        return eval(last_digit)
+    else:
+        return INVALID_ANS
+
+def extract_answer(completion):
+    try:
+        last_number = re.findall(r'\d+', completion)[-1]
+        return eval(last_number)
+    except:
+        return INVALID_ANS
+
+def is_correct( completion, answer):
+    gold = extract_answer(answer)
+    assert gold != INVALID_ANS, "No ground truth answer found in the document."
+    return extract_answer(completion) == gold
+
+if __name__ == '__main__':
+
+    parser = argparse.ArgumentParser(description='Test HF checkpoint.')
+    parser.add_argument("-c", "--checkpoint-path", type=Path, help="Checkpoint path", default="Qwen/Qwen-7B-Chat")
+    parser.add_argument("-f","--sample-input-file", type=str, default=None)
+    parser.add_argument("-o","--sample-output-file", type=str, default="gsm8k_res.jsonl")
+    parser.add_argument("--use-fewshot", action="store_true")
+
+    args = parser.parse_args()
+
+    if args.sample_input_file is not None:
+        dataset = load_from_disk(args.sample_input_file)# or: 
+    else:
+        dataset = load_dataset("gsm8k", "main")
+
+    print('Loading tokenizer ...')
+    tokenizer = AutoTokenizer.from_pretrained(args.checkpoint_path, trust_remote_code=True, bf16=True, use_flash_attn=True)
+
+    print('Loading model ...')
+    model = AutoModelForCausalLM.from_pretrained(args.checkpoint_path, device_map="auto", trust_remote_code=True).eval()
+    model.generation_config = GenerationConfig.from_pretrained(args.checkpoint_path, trust_remote_code=True)
+    model.generation_config.do_sample = False # use greedy decoding
+
+    test = dataset["test"]
+
+    f_output = open(args.sample_output_file, 'w', encoding='utf-8')
+    tot_length = test.num_rows
+    acc_res = []
+    for doc in tqdm.tqdm(test):
+        context = doc_to_text(doc, args.use_fewshot)
+        print(context)
+        completion = generate_sample(model, tokenizer, context)
+        answer = doc["answer"]
+        acc = is_correct(completion, answer)
+        doc["completion"] = completion
+        doc["acc"] = acc
+        f_output.write(json.dumps(doc, ensure_ascii=False) + "\n")
+        f_output.flush()
+        acc_res.append(acc)
+    
+    f_output.close()
+    print("4-shot Acc: " if args.use_fewshot else "Zero-shot Acc", np.mean(acc_res))

eval/evaluate_chat_humaneval.py

@@ -0,0 +1,82 @@
+import random
+import tqdm
+import os
+import sys
+import torch
+import jsonlines
+import argparse
+import jsonlines
+from pathlib import Path
+import re
+import textwrap
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers.generation import GenerationConfig
+
+"""
+Get the HumanEval.jsonl file from [here](https://github.com/openai/human-eval/tree/master/data)
+
+python eval/evaluate_chat_humaneval.py -f HumanEval.jsonl -o HumanEval_res.jsonl
+git clone https://github.com/openai/human-eval
+pip install -e human-eval
+evaluate_functional_correctness HumanEval_res.jsonl
+"""
+
+DEVICE = "cuda:0"
+
+def extract_code(text, entry_point):
+
+    # 正则表达式匹配代码块
+    code_block_pattern = re.compile(rf"```(?:[Pp]ython\n)?.*?def\s+{entry_point}.*?:\n(.*?)\n```", re.DOTALL)
+    code_block = code_block_pattern.search(text)
+    if code_block is None:
+        code_block_pattern = re.compile(rf"def\s+{entry_point}.*?:\n(.*?)(?:\n(?!\n*(?:  |\t))|$)", re.DOTALL)
+        code_block = code_block_pattern.search(text)
+    if code_block is None:
+        code_block_pattern = re.compile(rf"def.*?:\n(.*?)(?:\n(?!\n*(?:  |\t))|$)", re.DOTALL)
+        code_block = code_block_pattern.search(text)
+
+    if code_block is not None:
+        return code_block.group(1)
+    else:
+        # if no code block is found, assume the LM is simply filling the code
+        return textwrap.indent(text, ' ' * 4)
+
+def generate_sample(model, tokenizer, question, entry_point):
+    response, history = model.chat(
+        tokenizer,
+        question,
+        history=None,
+    )
+    print(question)
+    print(response)
+    answer = extract_code(response, entry_point)
+    return answer, response
+
+if __name__ == '__main__':
+
+    parser = argparse.ArgumentParser(description='Test HF checkpoint.')
+    parser.add_argument("-c", "--checkpoint-path", type=Path, help='Checkpoint path', default="Qwen/Qwen-7B-Chat")
+    parser.add_argument("-f","--sample-input-file", type=str, default=None, help="data path to HumanEval.jsonl")
+    parser.add_argument("-o","--sample-output-file", type=str, default="HumanEval_res.jsonl")
+
+
+    args = parser.parse_args()
+    print('Loading tokenizer ...')
+    tokenizer = AutoTokenizer.from_pretrained(args.checkpoint_path, trust_remote_code=True)
+
+    print('Loading model ...')
+    model = AutoModelForCausalLM.from_pretrained(args.checkpoint_path, device_map="auto", trust_remote_code=True, bf16=True, use_flash_attn=True).eval()
+    model.generation_config = GenerationConfig.from_pretrained(args.checkpoint_path, trust_remote_code=True)
+    model.generation_config.do_sample = False # use greedy decoding
+
+    f_output = jsonlines.Writer(open(args.sample_output_file, 'w', encoding='utf-8'))
+
+    f = jsonlines.open(args.sample_input_file)
+    with f_output as output:
+        for jobj in tqdm.tqdm(f, desc='task_idx'):
+            prompt = "Help me fill the following code.\n" + jobj['prompt']
+            task_id = jobj['task_id']
+            answer, response = generate_sample(model, tokenizer, prompt, jobj['entry_point'])
+            gen_jobjs = {'task_id': task_id, "completion": answer, 'response': response} 
+            output.write(gen_jobjs)
+    f_output.close()

eval/evaluate_chat_mmlu.py

@@ -0,0 +1,207 @@
+import os
+import pandas as pd
+import numpy as np
+import argparse
+import datasets
+import torch
+import re
+from thefuzz import process
+from typing import List
+from tqdm import tqdm
+from transformers.trainer_utils import set_seed
+
+'''
+wget https://people.eecs.berkeley.edu/~hendrycks/data.tar
+mkdir data/mmlu
+mv data.tar data/mmlu
+cd data/mmlu; tar xf data.tar
+cd ../../
+
+pip install thefuzz
+python eval/evaluate_chat_mmlu.py -d data/mmlu/data/
+'''
+
+def load_models_tokenizer(args):
+    from transformers import AutoModelForCausalLM, AutoTokenizer
+    from transformers.generation import GenerationConfig
+
+    tokenizer = AutoTokenizer.from_pretrained(args.checkpoint_path, trust_remote_code=True)
+    model = AutoModelForCausalLM.from_pretrained(args.checkpoint_path, device_map="auto", trust_remote_code=True, bf16=True, use_flash_attn=True).eval()
+    model.generation_config = GenerationConfig.from_pretrained(args.checkpoint_path, trust_remote_code=True)
+    model.generation_config.do_sample = False # use greedy decoding
+    return model, tokenizer
+
+
+def format_example(line):
+    example = 'The following is a multiple-choice question. Please choose the most suitable one among A, B, C and D as the answer to this question.\n\n' + line['question'] + "\n"
+    for choice in choices:
+        example += f'{choice}. {line[f"{choice}"]}\n'
+    return example
+
+
+def process_before_extraction(gen, choice_dict):
+    # replace the choice by letter in the generated sentence
+    # from longest one to shortest one
+    for key, val in sorted(choice_dict.items(), key=lambda x: len(x[1]), reverse=True):
+        pattern = re.compile(re.escape(val.rstrip(".")), re.IGNORECASE)
+        gen = pattern.sub(key, gen)
+    return gen
+
+def extract_choice(gen, choice_list):
+    # answer is A | choice is A | choose A
+    res = re.search(r"(?:(?:[Cc]hoose)|(?:(?:[Aa]nswer|[Cc]hoice)(?![^ABCD]{0,20}?(?:n't|not))[^ABCD]{0,10}?\b(?:|is|:|be))\b)[^ABCD]{0,20}?\b(A|B|C|D)\b", gen)
+
+    # A is correct | A is right
+    if res is None:
+        res = re.search(r"\b(A|B|C|D)\b(?![^ABCD]{0,8}?(?:n't|not)[^ABCD]{0,5}?(?:correct|right))[^ABCD]{0,10}?\b(?:correct|right)\b", gen)
+
+    # straight answer: A
+    if res is None:
+        res = re.search(r"^(A|B|C|D)(?:\.|,|:|$)", gen)
+
+    # simply extract the first appearred letter
+    if res is None:
+        res = re.search(r"(?<![a-zA-Z])(A|B|C|D)(?![a-zA-Z=])", gen)
+
+    if res is None:
+        return choices[choice_list.index(process.extractOne(gen, choice_list)[0])]
+    else:
+        return res.group(1)
+
+def extract_answer(response, row):
+    gen = process_before_extraction(response, {choice: row[choice] for choice in choices})
+    pred = extract_choice(gen, [row[choice] for choice in choices])
+    return pred
+
+@torch.no_grad()
+def eval_subject(
+        model,
+        tokenizer,
+        subject_name,
+        test_df,
+        save_result_dir=None,
+        overwrite=False,
+        **kwargs
+):
+    result_path = os.path.join(save_result_dir, f'{subject_name}_result.csv')
+    if not overwrite and os.path.exists(result_path):
+        print(f"{result_path} existed, skip!")
+        score = []
+        for (_, datarow), (_, resultrow) in zip(test_df.iterrows(), pd.read_csv(result_path).iterrows()):
+            # pred = extract_answer(resultrow['model_response'], datarow)
+            pred = resultrow['model_output']
+            correct = 1 if pred == datarow['answer'] else 0
+            score.append(correct)
+        return score
+
+    result = []
+    score = []
+
+    for _, row in tqdm(test_df.iterrows(), total=len(test_df)):
+        question = format_example(row)
+
+        response, history = model.chat(
+            tokenizer,
+            question,
+            history=None,
+        )
+        print(question)
+        print(response)
+        pred = extract_answer(response, row)
+        print(pred)
+        print("======================")
+
+        if 'answer' in row:
+            correct = 1 if pred == row['answer'] else 0
+            score.append(correct)
+            if args.debug: print(f'{question} pred: {pred} ref: {row["answer"]}')
+        result.append(pred)
+
+    if save_result_dir:
+        test_df['model_output'] = result
+        test_df['model_response'] = response
+        if score:
+            test_df["correctness"] = score
+        os.makedirs(save_result_dir, exist_ok=True)
+        test_df.to_csv(os.path.join(
+            save_result_dir, f'{subject_name}_result.csv'), encoding="utf-8", index=False)
+
+    return score
+
+
+def cal_mmlu(res):
+    acc_sum_dict = dict()
+    acc_norm_sum_dict = dict()
+    cnt_dict = dict()
+    acc_sum = 0.
+    cnt = 0
+    hard_cnt = 0
+    hard_acc_sum = 0.
+
+    for class_ in TASK_NAME_MAPPING.keys():
+        acc_sum_dict[class_] = 0.
+        acc_norm_sum_dict[class_] = 0.
+        cnt_dict[class_] = 0.
+
+        for tt in TASK_NAME_MAPPING[class_]:
+            acc_sum += sum(res[tt])
+            cnt += len(res[tt])
+
+            acc_sum_dict[class_] += sum(res[tt])
+            cnt_dict[class_] += len(res[tt])
+
+    print('\n\n\n')
+    for k in TASK_NAME_MAPPING.keys():
+        if k in cnt_dict:
+            print('%s ACC: %.2f ' % (
+                k, acc_sum_dict[k] * 100 / cnt_dict[k]))
+    print('AVERAGE ACC:%.2f ' % (acc_sum *100 / cnt))
+    
+
+def main(args):
+    print("loading model weights")
+    if args.checkpoint_path is not None:
+        model, tokenizer = load_models_tokenizer(args)
+    else:
+        model, tokenizer = None, None
+    print("model loaded")
+
+    dev_result = {}
+    for subject_name in tqdm(SUBJECTS):
+        # val_file_path = os.path.join(args.eval_data_path, 'val', f'{subject_name}_val.csv')
+        # dev_file_path = os.path.join(args.eval_data_path, 'dev', f'{subject_name}_dev.csv')
+        test_file_path = os.path.join(args.eval_data_path, 'test', f'{subject_name}_test.csv')
+        # val_df = pd.read_csv(val_file_path, names=['question','A','B','C','D','answer'])
+        # dev_df = pd.read_csv(dev_file_path, names=['question','A','B','C','D','answer'])
+        test_df = pd.read_csv(test_file_path, names=['question','A','B','C','D','answer'])
+
+        score = eval_subject(model, tokenizer, subject_name, test_df, save_result_dir=f"outs_chat/mmlu_eval_result", overwrite=args.overwrite)
+        dev_result[subject_name] = score
+    cal_mmlu(dev_result)
+
+
+TASK_NAME_MAPPING = {'stem': ['abstract_algebra', 'anatomy', 'astronomy', 'college_biology', 'college_chemistry', 'college_computer_science', 'college_mathematics', 'college_physics', 'computer_security', 'conceptual_physics', 'electrical_engineering', 'elementary_mathematics', 'high_school_biology', 'high_school_chemistry', 'high_school_computer_science', 'high_school_mathematics', 'high_school_physics', 'high_school_statistics', 'machine_learning'],
+ 'Humanities': ['formal_logic', 'high_school_european_history', 'high_school_us_history', 'high_school_world_history', 'international_law', 'jurisprudence', 'logical_fallacies', 'moral_disputes', 'moral_scenarios', 'philosophy', 'prehistory', 'professional_law', 'world_religions'],
+ 'other': ['business_ethics', 'college_medicine', 'human_aging', 'management', 'marketing', 'medical_genetics', 'miscellaneous', 'nutrition', 'professional_accounting', 'professional_medicine', 'virology', 'global_facts', 'clinical_knowledge'],
+ 'social': ['econometrics', 'high_school_geography', 'high_school_government_and_politics', 'high_school_macroeconomics', 'high_school_microeconomics', 'high_school_psychology', 'human_sexuality', 'professional_psychology', 'public_relations', 'security_studies', 'sociology', 'us_foreign_policy']}
+SUBJECTS = [v for vl in TASK_NAME_MAPPING.values() for v in vl]
+choices = ["A", "B", "C", "D"]
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser(description='Test HF checkpoint.')
+    parser.add_argument('-c', '--checkpoint-path', type=str, help='Checkpoint path', default="Qwen/Qwen-7B-Chat")
+    parser.add_argument('-s', '--seed', type=int, default=1234, help='Random seed')
+
+    """Provide extra arguments required for tasks."""
+    group = parser.add_argument_group(title='Evaluation options')
+    group.add_argument('-d', '--eval_data_path', type=str,
+                       help='Path to eval data')
+    group.add_argument("--debug", action='store_true', default=False,
+                       help='Print infos.')
+    group.add_argument("--overwrite", action='store_true', default=False,
+                       help='Overwrite existed results')
+
+    args = parser.parse_args()
+    set_seed(args.seed)
+
+    main(args)