我已经用我的大脑预先训练了BERT模型。
我使用的是一个微调过的Roberta模型，它是无偏有毒的--Roberta是在Jigsaw数据上训练的：
https://huggingface.co/unitary/unbiased-toxic-roberta

使用pytorch数据集创建数据

tokenizer = tr.RobertaTokenizer.from_pretrained("/home/pc/unbiased_toxic_roberta")
train_encodings = tokenizer(train_texts, truncation=True, padding=True, max_length=512, return_tensors="pt")

class SEDataset(torch.utils.data.Dataset):
    def __init__(self, encodings, labels):
        self.encodings = encodings
        self.labels = labels

    def __getitem__(self, idx):
        item = {key: torch.tensor(val[idx]) for key, val in self.encodings.items()}
        item['labels'] = torch.tensor(self.labels[idx])
        return item

    def __len__(self):
        return len(self.labels)

train_data = SEDataset(train_encodings, train_labels)


def compute_metrics(eval_pred):
    
    logits, labels = eval_pred
   

    predictions = np.argmax(logits, axis=-1)
    
    acc = np.sum(predictions == labels) / predictions.shape[0]
    
    return {"accuracy" : acc}

在预训练模型上添加几层的模型：

import torch.nn as nn
from transformers import AutoModel

class PosModel(nn.Module):
    def __init__(self):
        super(PosModel, self).__init__()
        
        self.base_model = tr.RobertaForSequenceClassification.from_pretrained('/home/pc/unbiased_toxic_roberta')
        self.dropout = nn.Dropout(0.5)
        self.linear = nn.Linear(768, 2) # output features from bert is 768 and 2 is ur number of labels
        
    def forward(self, input_ids, attn_mask):
        outputs = self.base_model(input_ids, attention_mask=attn_mask)
        # You write you new head here
        outputs = self.dropout(outputs[0])
        outputs = self.linear(outputs)
        
        return outputs

model = PosModel()

print(model)

培训步骤：
使用TrainingArguments将一些参数传递给模型

training_args = tr.TrainingArguments(
#     report_to = 'wandb',
    output_dir='/home/pc/1_Proj_hate_speech/results_roberta',          # output directory
    overwrite_output_dir = True,
    num_train_epochs=20,              # total number of training epochs
    per_device_train_batch_size=16,  # batch size per device during training
    per_device_eval_batch_size=32,   # batch size for evaluation
    learning_rate=2e-5,
    warmup_steps=1000,                # number of warmup steps for learning rate scheduler
    weight_decay=0.01,               # strength of weight decay
    logging_dir='./logs3',            # directory for storing logs
    logging_steps=1000,
    evaluation_strategy="epoch"
    ,save_strategy="epoch"
    ,load_best_model_at_end=True
)

trainer = tr.Trainer(
    model=model,                         # the instantiated 🤗 Transformers model to be trained
    args=training_args,                  # training arguments, defined above
    train_dataset=train_data,         # training dataset
    eval_dataset=val_data,             # evaluation dataset
    compute_metrics=compute_metrics
)

运行模型

trainer.train()

错误：

TypeError: Caught TypeError in replica 0 on device 0.
Original Traceback (most recent call last):
  File "/home/pc/.local/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 61, in _worker
    output = module(*input, **kwargs)
  File "/home/pc/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
    return forward_call(*input, **kwargs)
TypeError: forward() got an unexpected keyword argument 'input_ids'