环境配置

#安装mindnlp 0.4.0套件
!pip install mindnlp==0.4.0
!pip uninstall soundfile -y
!pip install download
!pip install jieba
!pip install https://ms-release.obs.cn-north-4.myhuaweicloud.com/2.3.1/MindSpore/unified/aarch64/mindspore-2.3.1-cp39-cp39-linux_aarch64.whl --trusted-host ms-release.obs.cn-north-4.myhuaweicloud.com -i https://pypi.tuna.tsinghua.edu.cn/simple

import os

import mindspore
from mindspore.dataset import text, GeneratorDataset, transforms
from mindspore import nn

from mindnlp.dataset import load_dataset

from mindnlp.engine import Trainer

imdb_ds = load_dataset('imdb', split=['train', 'test'])
imdb_train = imdb_ds['train']
imdb_test = imdb_ds['test']

imdb_train.get_dataset_size()

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 OpenAIGPTTokenizer
# tokenizer
gpt_tokenizer = OpenAIGPTTokenizer.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)

#这行代码是为了方便体验流程，把原本数据集的十分之一拿出来体验训练和评估,体验该完整的数据集，可以将这行代码注释掉
imdb_train, _ = imdb_train.split([0.1, 0.9], randomize=False)

# split train dataset into train and valid datasets
imdb_train, imdb_val = imdb_train.split([0.7, 0.3])

dataset_train = process_dataset(imdb_train, gpt_tokenizer, shuffle=True)
dataset_val = process_dataset(imdb_val, gpt_tokenizer)
dataset_test = process_dataset(imdb_test, gpt_tokenizer)

next(dataset_train.create_tuple_iterator())

from mindnlp.transformers import OpenAIGPTForSequenceClassification
from mindnlp import evaluate
import numpy as np

# set bert config and define parameters for training
model = OpenAIGPTForSequenceClassification.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)

from mindnlp.engine import TrainingArguments

training_args = TrainingArguments(
    output_dir="gpt_imdb_finetune",
    evaluation_strategy="epoch",
    save_strategy="epoch",
    logging_strategy="epoch",
    load_best_model_at_end=True,
    num_train_epochs=1.0,
    learning_rate=2e-5
)

metric = evaluate.load("accuracy")

def compute_metrics(eval_pred):
    logits, labels = eval_pred
    predictions = np.argmax(logits, axis=-1)
    return metric.compute(predictions=predictions, references=labels)

trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=dataset_train,
    eval_dataset=dataset_val,
    compute_metrics=compute_metrics
)

注: 如果想要运行的更快一些，可以在训练时需要V100的算力

trainer.train()

trainer.evaluate(dataset_test)

运行结果