你好请问代码中是否包含把微调后的模型保存下来的代码? import pandas as pd from sklearn import metrics from tqdm…
- User
你好请问代码中是否包含把微调后的模型保存下来的代码? import pandas as pd from sklearn import metrics from tqdm import tqdm import numpy as np import os os.environ['CUDA_VISIBLE_DEVICES']='6'
import torch from torch.utils.data import Dataset, DataLoader import torch.nn as nn import transformers
from torch import cuda
device = 'cuda' if cuda.is_available() else 'cpu'
df_train = pd.read_csv("/data/fl/distillbert-qa/train.csv")[[ "id", "Ofiicial Account Name","Title","News Url","Image Url","Report Content","label"
]]
def create_text(row): return (f"请判断以下新闻是真还是假,假新闻输出1,真新闻输出0.以下是一则新闻,新闻的账号发布信息为{row['Ofiicial Account Name']}," f"标题为{row['Title']},新闻链接为{row['News Url']}," f"标题图片链接为{row['Image Url']},举报内容为{row['Report Content']}.//")
应用该函数到 DataFrame 的每一行,创建新的 'text' 列
df_train['text'] = df_train.apply(create_text, axis=1)
创建一个新的 DataFrame,只包含 'text' 和 'label' 列
df_new = df_train[['text', 'label']]
如果需要,可以将新的 DataFrame 保存为 CSV 文件
df_new.to_csv("/data/fl/distillbert-qa/transformed_train.csv", index=False)
显示前几行以确认结果
print(df_new['text'].apply(len).max())
print(df_new.head()) MAX_LEN = 512 BATCH_SIZE = 32 LEARNING_RATE = 1e-05
DISTILL_BERT_PATH = '/data/fl/distillbert-qa/load' MODEL_PATH = "pytorch_model" tokenizer = transformers.DistilBertTokenizer.from_pretrained( DISTILL_BERT_PATH, do_lower_case=True )
class tweet_Dataset(Dataset):
def __init__(self, dataframe, tokenizer, max_len): self.data = dataframe self.tokenizer = tokenizer self.max_len = max_len def __getitem__(self, index): tweet = str(self.data.text[index]) tweet = " ".join(tweet.split()) inputs = self.tokenizer.encode_plus(tweet, None, add_special_tokens=True, max_length=self.max_len, pad_to_max_length=True, return_token_type_ids=True) ids = inputs['input_ids'] mask = inputs['attention_mask'] return { 'ids': torch.tensor(ids, dtype=torch.long), 'mask': torch.tensor(mask, dtype=torch.long), 'labels': torch.tensor(self.data.label[index], dtype=torch.float) } def __len__(self): return len(self.data)train_size = 0.85 train_dataset=df_new.sample(frac=train_size,random_state=200).reset_index(drop=True) valid_dataset=df_new.drop(train_dataset.index).reset_index(drop=True)
print("FULL Dataset: {}".format(df_new.shape)) print("TRAIN Dataset: {}".format(train_dataset.shape)) print("VALID Dataset: {}".format(valid_dataset.shape))
training_set = tweet_Dataset(train_dataset, tokenizer, MAX_LEN) testing_set = tweet_Dataset(valid_dataset, tokenizer, MAX_LEN)
training_set[0]
train_params = {'batch_size': BATCH_SIZE, 'shuffle': True, 'num_workers': 0 }
valid_params = {'batch_size': BATCH_SIZE, 'shuffle': True, 'num_workers': 0 }
train_dl = DataLoader(training_set, **train_params) valid_dl = DataLoader(testing_set, **valid_params)
class DistillBERTClass(torch.nn.Module): def init(self): super().init() self.distill_bert = transformers.DistilBertModel.from_pretrained(DISTILL_BERT_PATH) self.drop = torch.nn.Dropout(0.3) self.out = torch.nn.Linear(768, 1)
def forward(self, ids, mask): distilbert_output = self.distill_bert(ids, mask) hidden_state = distilbert_output[0] # (bs, seq_len, dim) pooled_output = hidden_state[:, 0] # (bs, dim) output_1 = self.drop(pooled_output) output = self.out(output_1) return outputmodel = DistillBERTClass() model.to(device)
def loss_fn(outputs, labels): return nn.BCEWithLogitsLoss()(outputs, labels)
optimizer = torch.optim.Adam(params=model.parameters(), lr=LEARNING_RATE)
def eval_fn(data_loader, model): model.eval() fin_labels = [] fin_outputs = [] with torch.no_grad(): for bi, d in tqdm(enumerate(data_loader), total=len(data_loader)): ids = d["ids"] mask = d["mask"] labels = d["labels"]
ids = ids.to(device, dtype=torch.long) mask = mask.to(device, dtype=torch.long) labels = labels.to(device, dtype=torch.float) outputs = model(ids=ids, mask=mask) fin_labels.extend(labels.cpu().detach().numpy().tolist()) fin_outputs.extend( torch.sigmoid(outputs).cpu().detach().numpy().tolist()) fin_outputs = np.array(fin_outputs) >= 0.5 f1_score = metrics.f1_score(fin_labels, fin_outputs) return f1_scoredef fit(num_epochs, model, loss_fn, opt, train_dl, valid_dl):
for epoch in range(num_epochs): model.train() for _,data in enumerate(train_dl, 0): ids = data['ids'].to(device, dtype = torch.long) mask = data['mask'].to(device, dtype = torch.long) labels = data['labels'].to(device, dtype = torch.float) outputs = model(ids, mask).squeeze() loss = loss_fn(outputs, labels) loss.backward() opt.step() opt.zero_grad() valid_acc = eval_fn(valid_dl, model) print('Epoch [{}/{}], Train Loss: {:.4f} and Validation acc {:.4f} and loss {:.4f}'.format(epoch+1, num_epochs, loss.item(),valid_acc, 1.1))fit(7, model, loss_fn, optimizer, train_dl, valid_dl)
def sentence_prediction(sentence): max_len = MAX_LEN tweet = str(sentence) tweet = " ".join(tweet.split()) inputs = tokenizer.encode_plus( tweet, None, add_special_tokens=True, max_length=max_len, pad_to_max_length=True, )
ids = inputs["input_ids"] mask = inputs["attention_mask"] ids = torch.tensor(ids, dtype=torch.long).unsqueeze(0) mask = torch.tensor(mask, dtype=torch.long).unsqueeze(0) ids = ids.to(device, dtype=torch.long) mask = mask.to(device, dtype=torch.long) outputs = model(ids=ids, mask=mask) outputs = torch.sigmoid(outputs).cpu().detach().numpy() return outputs[0][0] > 0.5 - Assistant
您好!根据您提供的代码,当前并没有包含将微调后的模型保存下来的代码。为了保存训练好的模型,您可以使用
torch.save()函数将模型的状态字典(state_dict)或整个模型进行保存。以下是两种常见的保存方式:
1. 只保存模型的状态字典
这是推荐的方式,因为它更灵活且与模型定义分离。
# 在训练完成后添加保存模型状态字典的代码 torch.save(model.state_dict(), 'distillbert_finetuned.pth') print("模型已保存为 distillbert_finetuned.pth")2. 保存整个模型
这种方式将模型的结构和参数一起保存,但通常不推荐,因为在加载时需要确保模型结构代码的一致性。
# 在训练完成后添加保存整个模型的代码 torch.save(model, 'distillbert_finetuned_model.pth') print("整个模型已保存为 distillbert_finetuned_model.pth")如何集成到您的代码中
可以在
fit函数的训练循环结束后,或者在训练完成后添加保存模型的代码。例如:def fit(num_epochs, model, loss_fn, opt, train_dl, valid_dl): for epoch in range(num_epochs): model.train() for _, data in enumerate(train_dl, 0): ids = data['ids'].to(device, dtype=torch.long) mask = data['mask'].to(device, dtype=torch.long) labels = data['labels'].to(device, dtype=torch.float) outputs = model(ids, mask).squeeze() loss = loss_fn(outputs, labels) loss.backward() opt.step() opt.zero_grad() valid_acc = eval_fn(valid_dl, model) print('Epoch [{}/{}], Train Loss: {:.4f} and Validation acc {:.4f} and loss {:.4f}'.format( epoch+1, num_epochs, loss.item(), valid_acc, 1.1)) # 训练结束后保存模型 torch.save(model.state_dict(), 'distillbert_finetuned.pth') print("模型已保存为 distillbert_finetuned.pth") # 开始训练并保存模型 fit(7, model, loss_fn, optimizer, train_dl, valid_dl)加载保存的模型
如果您只保存了
state_dict,加载模型时需要先定义模型结构,然后加载状态字典:# 定义模型结构 model = DistillBERTClass() model.to(device) # 加载状态字典 model.load_state_dict(torch.load('distillbert_finetuned.pth')) model.eval()如果您保存了整个模型,可以直接加载:
# 加载整个模型 model = torch.load('distillbert_finetuned_model.pth') model.to(device) model.eval()总结
当前代码中没有包含保存模型的部分。您可以根据上述方法,将保存模型的代码加入到训练流程的合适位置,以便在训练完成后保存您的微调模型。
如果有其他问题,欢迎继续提问!