基于MindSpore通过GPT实现情感分类
导入数据集
import os
import mindspore
from mindnlp._legacy.engine import Evaluator, Trainer
from mindnlp._legacy.engine.callbacks import BestModelCallback, CheckpointCallback
from mindnlp._legacy.metrics import Accuracy
from mindnlp.dataset import load_dataset
from mindspore import nn
from mindspore.dataset import GeneratorDataset, text, transforms
imdb_ds = load_dataset("imdb", split=["train", "test"])
imdb_train = imdb_ds["train"]
imdb_test = imdb_ds["test"]
对数据集进行预处理
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)
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",
)
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
导入 tokenizer
from mindnlp.transformers import GPTTokenizer
gpt_tokenizer = GPTTokenizer.from_pretrained("openai-gpt")
special_tokens_dict = {
"bos_token": "<bos>",
"eos_token": "<eos>",
"pad_token": "<pad>",
}
num_added_toks = gpt_tokenizer.add_special_tokens(special_tokens_dict)
分割训练数据集
imdb_train, imdb_val = imdb_train.split([0.7, 0.3])
导入训练模型
from mindnlp.transformers import GPTForSequenceClassification
from mindspore.experimental.optim import Adam
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()
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)
开始训练
trainer.run(tgt_columns="labels")
验证
evaluator = Evaluator(network=model, eval_dataset=dataset_test, metrics=metric)
evaluator.run(tgt_columns="labels")