前言
# 该案例在 mindnlp 0.3.1 版本完成适配,如果发现案例跑不通,可以指定mindnlp版本,执行`!pip install mindnlp==0.3.1`
!pip install mindnlp
!pip install jieba
%env HF_ENDPOINT=https://hf-mirror.com
导入对应的包
import os
import mindspore
from mindspore.dataset import text, GeneratorDataset, transforms
from mindspore import nn
from mindnlp.dataset import load_dataset
from mindnlp._legacy.engine import Trainer, Evaluator
from mindnlp._legacy.engine.callbacks import CheckpointCallback, BestModelCallback
from mindnlp._legacy.metrics import Accuracy
流程训练
import numpy as np
def process_dataset(dataset, tokenizer, max_seq_len=512, batch_size=4, shuffle=False):
is_ascend = mindspore.get_context('device_target') == 'Ascend'
def tokenize(text):
if is_ascend:
tokenized = tokenizer(text, padding='max_length', truncation=True, max_length=max_seq_len)
else:
tokenized = tokenizer(text, truncation=True, max_length=max_seq_len)
return tokenized['input_ids'], tokenized['attention_mask']
if shuffle:
dataset = dataset.shuffle(batch_size)
# map dataset
dataset = dataset.map(operations=[tokenize], input_columns="text", output_columns=['input_ids', 'attention_mask'])
dataset = dataset.map(operations=transforms.TypeCast(mindspore.int32), input_columns="label", output_columns="labels")
# batch dataset
if is_ascend:
dataset = dataset.batch(batch_size)
else:
dataset = dataset.padded_batch(batch_size, pad_info={'input_ids': (None, tokenizer.pad_token_id),
'attention_mask': (None, 0)})
return dataset
from mindnlp.transformers import GPTTokenizer
# tokenizer
gpt_tokenizer = GPTTokenizer.from_pretrained('openai-gpt')
# add sepcial token: <PAD>
special_tokens_dict = {
"bos_token": "<bos>",
"eos_token": "<eos>",
"pad_token": "<pad>",
}
num_added_toks = gpt_tokenizer.add_special_tokens(special_tokens_dict)
from mindnlp.transformers import GPTForSequenceClassification
from mindspore.experimental.optim import Adam
# set bert config and define parameters for training
model = GPTForSequenceClassification.from_pretrained('openai-gpt', num_labels=2)
model.config.pad_token_id = gpt_tokenizer.pad_token_id
model.resize_token_embeddings(model.config.vocab_size + 3)
optimizer = nn.Adam(model.trainable_params(), learning_rate=2e-5)
metric = Accuracy()
# define callbacks to save checkpoints
ckpoint_cb = CheckpointCallback(save_path='checkpoint', ckpt_name='gpt_imdb_finetune', epochs=1, keep_checkpoint_max=2)
best_model_cb = BestModelCallback(save_path='checkpoint', ckpt_name='gpt_imdb_finetune_best', auto_load=True)
trainer = Trainer(network=model, train_dataset=dataset_train,
eval_dataset=dataset_train, metrics=metric,
epochs=1, optimizer=optimizer, callbacks=[ckpoint_cb, best_model_cb],
jit=False)
总结
在情感分类任务中,首先通过`load_dataset`函数加载IMDB数据集,该数据集分为训练集和测试集,以确保有效利用标注好的电影评论进行模型训练和评估。在此过程中,还对数据进行预处理,包括去除无关字符和标准化文本格式,以提高模型效果。接下来,使用GPT Tokenizer对IMDB数据集中的评论进行分词,这一过程不仅将文本分割成单词或子词,还添加必要的特殊标记,如开始标记(<bos>)和结束标记(<eos>),确保模型能够正确理解文本结构和含义。最后,构建基于预训练GPT模型的情感分类模型,并根据IMDB数据集进行微调训练,以适应二分类任务的需求。