在 AI studio上运行paddlenlp的文本分类的例子，报BaseOffset的错，请问是什么问题啊？

trainer-0.log
[INFO]: current net device: , ip: 10.156.26.154
[INFO]: paddle job envs:
POD_IP=
PADDLE_PORT=12345
PADDLE_TRAINER_ID=0
PADDLE_TRAINERS_NUM=1
PADDLE_USE_CUDA=1
PADDLE_TRAINERS=
PADDLE_TRAINER_ID=0
PADDLE_PORTS_NUM=
NCCL_SOCKET_IFNAME=
PADDLE_IS_LOCAL=1
OUTPUT_PATH=/root/paddlejob/workspace/output
LOCAL_LOG_PATH=/root/paddlejob/workspace/log
cat: /mnt/ppoc_tmp_log/mount_path_list: No such file or directory
LOCAL_MOUNT_PATH=
JOB_ID=jobpf-5033911-179236-20221115144705
TRAINING_ROLE=TRAINER
[INFO]: user command: python train.py --batch_size 4 --model_name_or_path ernie-doc-base-zh --epoch 5 --output_dir ./checkpoints/
[INFO]: start trainer
[INFO]: output size checker pid: 334
~/paddlejob/workspace/code /mnt
/usr/local/lib/python3.7/dist-packages/pandas/compat/__init__.py:421: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
if LooseVersion(dateutil.__version__) < LooseVersion('2.5'):
/usr/local/lib/python3.7/dist-packages/pandas/compat/numpy/__init__.py:11: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
_nlv = LooseVersion(_np_version)
/usr/local/lib/python3.7/dist-packages/pandas/compat/numpy/__init__.py:12: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
_np_version_under1p10 = _nlv < LooseVersion('1.10')
/usr/local/lib/python3.7/dist-packages/pandas/compat/numpy/__init__.py:13: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
_np_version_under1p11 = _nlv < LooseVersion('1.11')
/usr/local/lib/python3.7/dist-packages/pandas/compat/numpy/__init__.py:14: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
_np_version_under1p12 = _nlv < LooseVersion('1.12')
/usr/local/lib/python3.7/dist-packages/pandas/compat/numpy/__init__.py:15: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
_np_version_under1p13 = _nlv < LooseVersion('1.13')
/usr/local/lib/python3.7/dist-packages/pandas/compat/numpy/__init__.py:16: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
_np_version_under1p14 = _nlv < LooseVersion('1.14')
/usr/local/lib/python3.7/dist-packages/pandas/compat/numpy/__init__.py:17: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
_np_version_under1p15 = _nlv < LooseVersion('1.15')
/usr/local/lib/python3.7/dist-packages/setuptools/_distutils/version.py:346: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
other = LooseVersion(other)
/usr/local/lib/python3.7/dist-packages/pandas/core/dtypes/inference.py:6: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated since Python 3.3,and in 3.9 it will stop working
from collections import Iterable
/usr/local/lib/python3.7/dist-packages/pandas/core/tools/datetimes.py:3: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated since Python 3.3,and in 3.9 it will stop working
from collections import MutableMapping
Traceback (most recent call last):
File "train.py", line 26, in
from modeling import ErnieDocForSequenceClassification
File "/root/paddlejob/workspace/code/modeling.py", line 18, in
from paddlenlp.transformers.attention_utils import _convert_param_attr_to_list
File "/usr/local/lib/python3.7/dist-packages/paddlenlp/__init__.py", line 25, in
from . import datasets
File "/usr/local/lib/python3.7/dist-packages/paddlenlp/datasets/__init__.py", line 15, in
from .dataset import *
File "/usr/local/lib/python3.7/dist-packages/paddlenlp/datasets/dataset.py", line 27, in
import datasets
File "/usr/local/lib/python3.7/dist-packages/datasets/__init__.py", line 37, in
from .arrow_dataset import Dataset
File "/usr/local/lib/python3.7/dist-packages/datasets/arrow_dataset.py", line 52, in
import pandas as pd
File "/usr/local/lib/python3.7/dist-packages/pandas/__init__.py", line 42, in
from pandas.core.api import *
File "/usr/local/lib/python3.7/dist-packages/pandas/core/api.py", line 10, in
from pandas.core.groupby.groupby import Grouper
File "/usr/local/lib/python3.7/dist-packages/pandas/core/groupby/__init__.py", line 2, in
from pandas.core.groupby.groupby import (
File "/usr/local/lib/python3.7/dist-packages/pandas/core/groupby/groupby.py", line 46, in
from pandas.core.index import (Index, MultiIndex,
File "/usr/local/lib/python3.7/dist-packages/pandas/core/index.py", line 2, in
from pandas.core.indexes.api import *
File "/usr/local/lib/python3.7/dist-packages/pandas/core/indexes/api.py", line 4, in
from pandas.core.indexes.base import (Index,
File "/usr/local/lib/python3.7/dist-packages/pandas/core/indexes/base.py", line 53, in
from pandas.core import ops
File "/usr/local/lib/python3.7/dist-packages/pandas/core/ops/__init__.py", line 32, in
from pandas.core.ops.array_ops import ( # noqa:F401
File "/usr/local/lib/python3.7/dist-packages/pandas/core/ops/array_ops.py", line 19, in
from pandas._libs.tslibs import BaseOffset
ImportError: cannot import name 'BaseOffset' from 'pandas._libs.tslibs' (/usr/local/lib/python3.7/dist-packages/pandas/_libs/tslibs/__init__.py)
/mnt
[INFO]: kill size_checker_id 334
[INFO]: train job success!