SwanLab入门深度学习：Qwen3大模型指令微调

import json import pandas as pd import torch from datasets import Dataset from modelscope import snapshot_download, AutoTokenizer from swanlab.integration.huggingface import SwanLabCallback from peft import LoraConfig, TaskType, get_peft_model from transformers import AutoModelForCausalLM, TrainingArguments, Trainer, DataCollatorForSeq2Seq import os import swanlab def dataset_jsonl_transfer(origin_path, new_path): """ 将原始数据集转换为大模型微调所需数据格式的新数据集 """ messages = [] # 读取旧的JSONL文件 with open(origin_path, "r", encoding="utf-8") as file: for line in file: # 解析每一行的json数据 data = json.loads(line) context = data["text"] catagory = data["category"] label = data["output"] message = { "instruction": "你是一个文本分类领域的专家，你会接收到一段文本和几个潜在的分类选项，请输出文本内容的正确类型", "input": f"文本:{context},类型选型:{catagory}", "output": label, } messages.append(message) # 保存重构后的JSONL文件 with open(new_path, "w", encoding="utf-8") as file: for message in messages: file.write(json.dumps(message, ensure_ascii=False) + " ") def process_func(example): """ 将数据集进行预处理 """ MAX_LENGTH = 384 input_ids, attention_mask, labels = [], [], [] instruction = tokenizer( f"<|im_start|>system 你是一个文本分类领域的专家，你会接收到一段文本和几个潜在的分类选项，请输出文本内容的正确类型<|im_end|> <|im_start|>user {example['input']}<|im_end|> <|im_start|>assistant ", add_special_tokens=False, ) response = tokenizer(f"{example['output']}", add_special_tokens=False) input_ids = instruction["input_ids"] + response["input_ids"] + [tokenizer.pad_token_id] attention_mask = ( instruction["attention_mask"] + response["attention_mask"] + [1] ) labels = [-100] * len(instruction["input_ids"]) + response["input_ids"] + [tokenizer.pad_token_id] if len(input_ids) > MAX_LENGTH: # 做一个截断 input_ids = input_ids[:MAX_LENGTH] attention_mask = attention_mask[:MAX_LENGTH] labels = labels[:MAX_LENGTH] return {"input_ids": input_ids, "attention_mask": attention_mask, "labels": labels} def predict(messages, model, tokenizer): device = "cuda" text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) model_inputs = tokenizer([text], return_tensors="pt").to(device) generated_ids = model.generate( model_inputs.input_ids, max_new_tokens=512 ) generated_ids = [ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) ] response = tokenizer.batch_decode( generated_ids, skip_special_tokens=True)[0] print(response) return response # 在modelscope上下载Qwen模型到本地目录下 # model_dir = snapshot_download("qwen/Qwen2-1.5B-Instruct", cache_dir="./", revision="master") # Transformers加载模型权重 tokenizer = AutoTokenizer.from_pretrained( "./Qwen/Qwen3-1.7B/", use_fast=False, trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained( "./Qwen/Qwen3-1.7B/", device_map="auto", torch_dtype=torch.bfloat16) model.enable_input_require_grads() # 开启梯度检查点时，要执行该方法 # 加载、处理数据集和测试集 train_dataset_path = "./zh_cls_fudan-news/train.jsonl" test_dataset_path = "./zh_cls_fudan-news/test.jsonl" train_jsonl_new_path = "new_train.jsonl" test_jsonl_new_path = "new_test.jsonl" if not os.path.exists(train_jsonl_new_path): dataset_jsonl_transfer(train_dataset_path, train_jsonl_new_path) if not os.path.exists(test_jsonl_new_path): dataset_jsonl_transfer(test_dataset_path, test_jsonl_new_path) # 得到训练集 train_df = pd.read_json(train_jsonl_new_path, lines=True) train_ds = Dataset.from_pandas(train_df) train_dataset = train_ds.map( process_func, remove_columns=train_ds.column_names) config = LoraConfig( task_type=TaskType.CAUSAL_LM, target_modules=["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"], inference_mode=False, # 训练模式 r=8, # Lora 秩 lora_alpha=32, # Lora alaph，具体作用参见 Lora 原理 lora_dropout=0.1, # Dropout 比例 ) model = get_peft_model(model, config) args = TrainingArguments( output_dir="./output/Qwen3-zh_cls_fudan-news", per_device_train_batch_size=4, gradient_accumulation_steps=4, logging_steps=10, num_train_epochs=2, save_steps=100, learning_rate=1e-4, save_on_each_node=True, gradient_checkpointing=True, report_to="none", ) swanlab_callback = SwanLabCallback( project="Qwen3-fintune", experiment_name="Qwen3-1.7B", description="使用通义千问Qwen3-1.7B模型在zh_cls_fudan-news数据集上微调。", config= ) # 开始微调 trainer = Trainer( model=model, args=args, train_dataset=train_dataset, data_collator=DataCollatorForSeq2Seq(tokenizer=tokenizer, padding=True), callbacks=[swanlab_callback], ) trainer.train() # 保存模型和分词器 output_dir = "./output/Qwen3-zh_cls_fudan-news" # 保存整个模型 model.save_pretrained(output_dir, save_config=千问 Qwen 教程True) tokenizer.save_pretrained(output_dir) # 用测试集的前10条，测试模型 test_df = pd.read_json(test_jsonl_new_path, lines=True)[:10] test_text_list = [] for index, row in test_df.iterrows(): instruction = row['instruction'] input_value = row['input'] messages = [ {"role": "system", "content": f"{instruction}"}, {"role": "user", "content": f"{input_value}"} ] response = predict(messages, model, tokenizer) messages.append({"role": "assistant", "content": f"{response}"}) result_text = f"{messages[0]} {messages[1]} {messages[2]}" test_text_list.append(swanlab.Text(result_text, caption=response)) swanlab.log({"Prediction": test_text_list}) swanlab.finish()