各位大佬，想请教一下代码前面都正常，运行到df.to_csv就报错是哪出了问题啊

[tutulovecat]

    mconf = GPTConfig(train_dataset.vocab_size, train_dataset.max_len, num_props=num_props,  # args.num_props,
                        n_layer=args.n_layer, n_head=args.n_head, n_embd=args.n_embd, scaffold=args.scaffold, scaffold_maxlen=scaffold_max_len,
                        lstm=args.lstm, lstm_layers=args.lstm_layers)
    model = GPT(mconf)

    tconf = TrainerConfig(max_epochs=args.max_epochs, batch_size=args.batch_size, learning_rate=args.learning_rate,
                            lr_decay=True, warmup_tokens=0.1*len(train_data)*max_len, final_tokens=args.max_epochs*len(train_data)*max_len,
                            num_workers=10, ckpt_path=f'D:/Jupyter/MolGPT/train-copy1/cond_gpt/weights/{args.run_name}.pt', block_size=train_dataset.max_len, generate=False)
    trainer = Trainer(model, train_dataset, valid_dataset,
                        tconf, train_dataset.stoi, train_dataset.itos)
    df = trainer.train(wandb)

    df.to_csv(f'D:/Jupyter/MolGPT/train-copy1/{args.run_name}.csv', index=False)

报错为

AttributeError                            Traceback (most recent call last)
Cell In[3], line 76
     72 trainer = Trainer(model, train_dataset, valid_dataset,
     73                     tconf, train_dataset.stoi, train_dataset.itos)
     74 df = trainer.train(wandb)
---> 76 df.to_csv(f'D:/Jupyter/MolGPT/train-copy1/{args.run_name}.csv', index=False)

AttributeError: 'NoneType' object has no attribute 'to_csv'

[T0BSky]

报错信息显示'NoneType' object has no attribute 'to_csv'，意味着df是None类型，而不是一个DataFrame对象，因此无法调用to_csv方法。这通常是因为trainer.train(wandb)返回了None，而不是一个DataFrame对象。你可以在trainer.train(wandb)之后添加一些调试语句，例如打印df，查看其返回值是什么，以便找出问题所在。可能需要检查Trainer.train方法的实现，确保它返回一个正确的DataFrame对象。