Python 如何在Squad2.0上微调BERT

我对伯特真的很陌生，我想在谷歌Colab上微调伯特的基本模型。基本上，我使用GPU进行设置，下载数据并尝试调用python run_squad.py

!git clone https://github.com/google-research/bert.git

!wget https://storage.googleapis.com/bert_models/2018_10_18/uncased_L-12_H-768_A-12.zip
!unzip the file
!unzip uncased_L-12_H-768_A-12.zip

import tensorflow as tf

# Get the GPU device name.
device_name = tf.test.gpu_device_name()

# The device name should look like the following:
if device_name == '/device:GPU:0':
    print('Found GPU at: {}'.format(device_name))
else:
    raise SystemError('GPU device not found')

import torch

# If there's a GPU available...
if torch.cuda.is_available():    

    # Tell PyTorch to use the GPU.    
    device = torch.device("cuda")

    print('There are %d GPU(s) available.' % torch.cuda.device_count())

    print('We will use the GPU:', torch.cuda.get_device_name(0))

# If not...
else:
    print('No GPU available, using the CPU instead.')
    device = torch.device("cpu")

!pip install transformers
!pip install wget

import wget
import os

print('Downloading dataset...')

# The URL for the dataset zip file.
url = 'https://rajpurkar.github.io/SQuAD-explorer/dataset/train-v2.0.json'

# Download the file (if we haven't already)
if not os.path.exists('./train-v2.0.json'):
    wget.download(url, './train-v2.0.json')

# The URL for the dataset zip file.
url = 'https://rajpurkar.github.io/SQuAD-explorer/dataset/dev-v2.0.json'

# Download the file (if we haven't already)
if not os.path.exists('./dev-v2.0.json'):
    wget.download(url, './dev-v2.0.json')

print('Done')

# Unzip the dataset (if we haven't already)
if not os.path.exists('./bert-master/'):
    !unzip bert-master.zip

!pip install tensorflow-gpu==1.15.0

上面的代码基本上确保我已经设置了GPU，获得了所需的依赖项，并下载了Squad2.0数据。下一步是给run_squad.py打电话，这就是我迷路的地方。这是我的文件位置

我运行了这个单元，得到了一个错误：python3。我认为我正确配置了路径，为什么它仍然缺少bert_config.json

WARNING:tensorflow:From /content/bert-master/optimization.py:87: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.Optimizer instead.

WARNING:tensorflow:From bert-master/run_squad.py:1283: The name tf.app.run is deprecated. Please use tf.compat.v1.app.run instead.

WARNING:tensorflow:From bert-master/run_squad.py:1127: The name tf.logging.set_verbosity is deprecated. Please use tf.compat.v1.logging.set_verbosity instead.

W0519 08:02:09.023542 140027033761664 module_wrapper.py:139] From bert-master/run_squad.py:1127: The name tf.logging.set_verbosity is deprecated. Please use tf.compat.v1.logging.set_verbosity instead.

WARNING:tensorflow:From bert-master/run_squad.py:1127: The name tf.logging.INFO is deprecated. Please use tf.compat.v1.logging.INFO instead.

W0519 08:02:09.023784 140027033761664 module_wrapper.py:139] From bert-master/run_squad.py:1127: The name tf.logging.INFO is deprecated. Please use tf.compat.v1.logging.INFO instead.

WARNING:tensorflow:From /content/bert-master/modeling.py:93: The name tf.gfile.GFile is deprecated. Please use tf.io.gfile.GFile instead.

W0519 08:02:09.024012 140027033761664 module_wrapper.py:139] From /content/bert-master/modeling.py:93: The name tf.gfile.GFile is deprecated. Please use tf.io.gfile.GFile instead.

Traceback (most recent call last):
  File "bert-master/run_squad.py", line 1283, in <module>
    tf.app.run()
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/platform/app.py", line 40, in run
    _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
  File "/usr/local/lib/python3.6/dist-packages/absl/app.py", line 299, in run
    _run_main(main, args)
  File "/usr/local/lib/python3.6/dist-packages/absl/app.py", line 250, in _run_main
    sys.exit(main(argv))
  File "bert-master/run_squad.py", line 1129, in main
    bert_config = modeling.BertConfig.from_json_file(FLAGS.bert_config_file)
  File "/content/bert-master/modeling.py", line 94, in from_json_file
    text = reader.read()
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/lib/io/file_io.py", line 122, in read
    self._preread_check()
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/lib/io/file_io.py", line 84, in _preread_check
    compat.as_bytes(self.__name), 1024 * 512)
tensorflow.python.framework.errors_impl.NotFoundError: /bert_config.json; No such file or directory

警告：tensorflow:From/content/bert master/optimization.py:87:名称tf.train.Optimizer已被弃用。请改用tf.compat.v1.train.Optimizer。
警告：tensorflow:来自bert master/run_squad.py:1283:名称tf.app.run已弃用。请改用tf.compat.v1.app.run。
警告：tensorflow:来自bert master/run_squad.py:1127:不推荐使用名称tf.logging.set_verbosity。请改用tf.compat.v1.logging.set\u详细信息。
W0519 08:02:09.023542 140027033761664模块_wrapper.py:139]来自bert master/run_squad.py:1127:不推荐使用名称tf.logging.set_verbosity。请改用tf.compat.v1.logging.set\u详细信息。
警告：tensorflow:来自bert master/run_squad.py:1127:名称tf.logging.INFO已弃用。请改用tf.compat.v1.logging.INFO。
W0519 08:02:09.023784 140027033761664模块_wrapper.py:139]来自bert master/run_squad.py:1127:名称tf.logging.INFO已弃用。请改用tf.compat.v1.logging.INFO。
警告：tensorflow:From/content/bert master/modeling.py:93:不推荐使用tf.gfile.gfile名称。请改用tf.io.gfile.gfile。
W0519 08:02:09.024012 140027033761664模块_wrapper.py:139]From/content/bert master/modeling.py:93:不推荐使用tf.gfile.gfile名称。请改用tf.io.gfile.gfile。
回溯（最近一次呼叫最后一次）：
文件“bert master/run_squad.py”，第1283行，在
tf.app.run（）
文件“/usr/local/lib/python3.6/dist packages/tensorflow_core/python/platform/app.py”，第40行，正在运行
_运行（main=main，argv=argv，flags\u parser=\u parse\u flags\u tolerate\u unde）
文件“/usr/local/lib/python3.6/dist-packages/absl/app.py”，第299行，运行中
_运行_main（main，args）
文件“/usr/local/lib/python3.6/dist-packages/absl/app.py”，第250行，在主
系统出口（主（argv））
文件“bert master/run_squad.py”，第1129行，主目录
bert_config=modeling.BertConfig.from_json_文件（FLAGS.bert_config_文件）
文件“/content/bert master/modeling.py”，第94行，在from_json_文件中
text=reader.read（）
文件“/usr/local/lib/python3.6/dist packages/tensorflow_core/python/lib/io/File_io.py”，第122行，已读
self.\u预读\u检查（）
文件“/usr/local/lib/python3.6/dist packages/tensorflow\u core/python/lib/io/File\u io.py”，第84行，在预读检查中
兼容字节（自身名称），1024*512）
tensorflow.python.framework.errors\u impl.NotFoundError:/bert\u config.json；没有这样的文件或目录

在

导出BERT\u BASE\u DIR=.…

之后，你能发布

ls$BERT\u BASE\u DIR/vocab.txt的响应吗

我认为它必须是

导出BERT\u BASE\u DIR=./未加密的L-12\u H-768\u A-12

看看这个：它有用于二进制、多类和多标签文本分类的Google Colab笔记本，在GPU上运行的

export-BERT\u BASE\u DIR=.…

之后，你能发布

ls$BERT\u BASE\u DIR/vocab.txt的响应吗？

我认为它必须是

export-BERT\u BASE\u DIR=./uncased\u L-12\u H-768\u A-12

看看这个：它有用于二进制、多类和多标签文本分类的Google Colab笔记本，在GPU上运行

WARNING:tensorflow:From /content/bert-master/optimization.py:87: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.Optimizer instead.

WARNING:tensorflow:From bert-master/run_squad.py:1283: The name tf.app.run is deprecated. Please use tf.compat.v1.app.run instead.

WARNING:tensorflow:From bert-master/run_squad.py:1127: The name tf.logging.set_verbosity is deprecated. Please use tf.compat.v1.logging.set_verbosity instead.

W0519 08:02:09.023542 140027033761664 module_wrapper.py:139] From bert-master/run_squad.py:1127: The name tf.logging.set_verbosity is deprecated. Please use tf.compat.v1.logging.set_verbosity instead.

WARNING:tensorflow:From bert-master/run_squad.py:1127: The name tf.logging.INFO is deprecated. Please use tf.compat.v1.logging.INFO instead.

W0519 08:02:09.023784 140027033761664 module_wrapper.py:139] From bert-master/run_squad.py:1127: The name tf.logging.INFO is deprecated. Please use tf.compat.v1.logging.INFO instead.

WARNING:tensorflow:From /content/bert-master/modeling.py:93: The name tf.gfile.GFile is deprecated. Please use tf.io.gfile.GFile instead.

W0519 08:02:09.024012 140027033761664 module_wrapper.py:139] From /content/bert-master/modeling.py:93: The name tf.gfile.GFile is deprecated. Please use tf.io.gfile.GFile instead.

Traceback (most recent call last):
  File "bert-master/run_squad.py", line 1283, in <module>
    tf.app.run()
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/platform/app.py", line 40, in run
    _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
  File "/usr/local/lib/python3.6/dist-packages/absl/app.py", line 299, in run
    _run_main(main, args)
  File "/usr/local/lib/python3.6/dist-packages/absl/app.py", line 250, in _run_main
    sys.exit(main(argv))
  File "bert-master/run_squad.py", line 1129, in main
    bert_config = modeling.BertConfig.from_json_file(FLAGS.bert_config_file)
  File "/content/bert-master/modeling.py", line 94, in from_json_file
    text = reader.read()
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/lib/io/file_io.py", line 122, in read
    self._preread_check()
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/lib/io/file_io.py", line 84, in _preread_check
    compat.as_bytes(self.__name), 1024 * 512)
tensorflow.python.framework.errors_impl.NotFoundError: /bert_config.json; No such file or directory