Errata

# hide
from transformers import pipeline, set_seed

It generates the warnings and error message below:

ARNING:tensorflow:From C:\Users\ziad.elmously.MLCORP\Anaconda3\envs\LargeLanguageModels\lib\site-packages\keras\src\losses.py:2976: The name tf.losses.sparse_softmax_cross_entropy is deprecated. Please use tf.compat.v1.losses.sparse_softmax_cross_entropy instead.

---------------------------------------------------------------------------
ModuleNotFoundError Traceback (most recent call last)
File ~\Anaconda3\envs\LargeLanguageModels\lib\site-packages\transformers\file_utils.py:2704, in _LazyModule._get_module(self, module_name)
2703 try:
-> 2704 return importlib.import_module("." + module_name, self.__name__)
2705 except Exception as e:

File ~\Anaconda3\envs\LargeLanguageModels\lib\importlib\__init__.py:127, in import_module(name, package)
126 level += 1
--> 127 return _bootstrap._gcd_import(name[level:], package, level)

File <frozen importlib._bootstrap>:1030, in _gcd_import(name, package, level)

File <frozen importlib._bootstrap>:1007, in _find_and_load(name, import_)

File <frozen importlib._bootstrap>:986, in _find_and_load_unlocked(name, import_)

File <frozen importlib._bootstrap>:680, in _load_unlocked(spec)

File <frozen importlib._bootstrap_external>:850, in exec_module(self, module)

File <frozen importlib._bootstrap>:228, in _call_with_frames_removed(f, *args, **kwds)

File ~\Anaconda3\envs\LargeLanguageModels\lib\site-packages\transformers\pipelines\__init__.py:54
53 from .question_answering import QuestionAnsweringArgumentHandler, QuestionAnsweringPipeline
---> 54 from .table_question_answering import TableQuestionAnsweringArgumentHandler, TableQuestionAnsweringPipeline
55 from .text2text_generation import SummarizationPipeline, Text2TextGenerationPipeline, TranslationPipeline

File ~\Anaconda3\envs\LargeLanguageModels\lib\site-packages\transformers\pipelines\table_question_answering.py:24
22 import tensorflow as tf
---> 24 import tensorflow_probability as tfp
26 from ..models.auto.modeling_tf_auto import TF_MODEL_FOR_TABLE_QUESTION_ANSWERING_MAPPING

File ~\AppData\Roaming\Python\Python39\site-packages\tensorflow_probability\__init__.py:20
17 # Contributors to the `python/` dir should not alter this file; instead update
18 # `python/__init__.py` as necessary.
---> 20 from tensorflow_probability import substrates
21 # from tensorflow_probability.google import staging # DisableOnExport
22 # from tensorflow_probability.google import tfp_google # DisableOnExport

File ~\AppData\Roaming\Python\Python39\site-packages\tensorflow_probability\substrates\__init__.py:17
15 """TensorFlow Probability alternative substrates."""
---> 17 from tensorflow_probability.python.internal import all_util
18 from tensorflow_probability.python.internal import lazy_loader # pylint: disable=g-direct-tensorflow-import

File ~\AppData\Roaming\Python\Python39\site-packages\tensorflow_probability\python\__init__.py:138
137 for pkg_name in _maybe_nonlazy_load:
--> 138 dir(globals()[pkg_name]) # Forces loading the package from its lazy loader.
141 all_util.remove_undocumented(__name__, _lazy_load + _maybe_nonlazy_load)

File ~\AppData\Roaming\Python\Python39\site-packages\tensorflow_probability\python\internal\lazy_loader.py:57, in LazyLoader.__dir__(self)
56 def __dir__(self):
---> 57 module = self._load()
58 return dir(module)

File ~\AppData\Roaming\Python\Python39\site-packages\tensorflow_probability\python\internal\lazy_loader.py:40, in LazyLoader._load(self)
39 # Import the target module and insert it into the parent's namespace
---> 40 module = importlib.import_module(self.__name__)
41 if self._parent_module_globals is not None:

File ~\Anaconda3\envs\LargeLanguageModels\lib\importlib\__init__.py:127, in import_module(name, package)
126 level += 1
--> 127 return _bootstrap._gcd_import(name[level:], package, level)

File ~\AppData\Roaming\Python\Python39\site-packages\tensorflow_probability\python\experimental\__init__.py:31
30 from tensorflow_probability.python.experimental import auto_batching
---> 31 from tensorflow_probability.python.experimental import bijectors
32 from tensorflow_probability.python.experimental import distribute

File ~\AppData\Roaming\Python\Python39\site-packages\tensorflow_probability\python\experimental\bijectors\__init__.py:17
15 """TensorFlow Probability experimental bijectors package."""
---> 17 from tensorflow_probability.python.bijectors.ldj_ratio import forward_log_det_jacobian_ratio
18 from tensorflow_probability.python.bijectors.ldj_ratio import inverse_log_det_jacobian_ratio

File ~\AppData\Roaming\Python\Python39\site-packages\tensorflow_probability\python\bijectors\__init__.py:19
17 # pylint: disable=unused-import,wildcard-import,line-too-long,g-importing-member
---> 19 from tensorflow_probability.python.bijectors.absolute_value import AbsoluteValue
20 from tensorflow_probability.python.bijectors.ascending import Ascending

File ~\AppData\Roaming\Python\Python39\site-packages\tensorflow_probability\python\bijectors\absolute_value.py:19
17 import tensorflow.compat.v2 as tf
---> 19 from tensorflow_probability.python.bijectors import bijector
20 from tensorflow_probability.python.internal import assert_util

File ~\AppData\Roaming\Python\Python39\site-packages\tensorflow_probability\python\bijectors\bijector.py:26
25 from tensorflow_probability.python.internal import auto_composite_tensor
---> 26 from tensorflow_probability.python.internal import batch_shape_lib
27 from tensorflow_probability.python.internal import cache_util

File ~\AppData\Roaming\Python\Python39\site-packages\tensorflow_probability\python\internal\batch_shape_lib.py:23
21 import tensorflow.compat.v2 as tf
---> 23 from tensorflow_probability.python.internal import prefer_static as ps
24 from tensorflow_probability.python.internal import tensor_util

File ~\AppData\Roaming\Python\Python39\site-packages\tensorflow_probability\python\internal\prefer_static.py:26
25 from tensorflow_probability.python.internal import tensorshape_util
---> 26 from tensorflow_probability.python.internal.backend import numpy as nptf
28 from tensorflow.python.framework import ops # pylint: disable=g-direct-tensorflow-import

File ~\AppData\Roaming\Python\Python39\site-packages\tensorflow_probability\python\internal\backend\numpy\__init__.py:18
17 from tensorflow_probability.python.internal.backend.numpy import __internal__
---> 18 from tensorflow_probability.python.internal.backend.numpy import bitwise
19 from tensorflow_probability.python.internal.backend.numpy import compat

File ~\AppData\Roaming\Python\Python39\site-packages\tensorflow_probability\python\internal\backend\numpy\bitwise.py:19
17 import numpy as np
---> 19 from tensorflow_probability.python.internal.backend.numpy import _utils as utils
21 __all__ = [
22 'bitwise_xor',
23 'left_shift',
24 ]

File ~\AppData\Roaming\Python\Python39\site-packages\tensorflow_probability\python\internal\backend\numpy\_utils.py:22
21 import numpy as np
---> 22 from tensorflow_probability.python.internal.backend.numpy import nest
24 try:

File ~\AppData\Roaming\Python\Python39\site-packages\tensorflow_probability\python\internal\backend\numpy\nest.py:30
29 import types
---> 30 import tree as dm_tree
32 # pylint: disable=g-import-not-at-top

ModuleNotFoundError: No module named 'tree'

The above exception was the direct cause of the following exception:

RuntimeError Traceback (most recent call last)
Cell In[1], line 2
1 # hide
----> 2 from transformers import pipeline, set_seed

File <frozen importlib._bootstrap>:1055, in _handle_fromlist(module, fromlist, import_, recursive)

File ~\Anaconda3\envs\LargeLanguageModels\lib\site-packages\transformers\file_utils.py:2694, in _LazyModule.__getattr__(self, name)
2692 value = self._get_module(name)
2693 elif name in self._class_to_module.keys():
-> 2694 module = self._get_module(self._class_to_module[name])
2695 value = getattr(module, name)
2696 else:

File ~\Anaconda3\envs\LargeLanguageModels\lib\site-packages\transformers\file_utils.py:2706, in _LazyModule._get_module(self, module_name)
2704 return importlib.import_module("." + module_name, self.__name__)
2705 except Exception as e:
-> 2706 raise RuntimeError(
2707 f"Failed to import {self.__name__}.{module_name} because of the following error (look up to see its traceback):\n{e}"
2708 ) from e

RuntimeError: Failed to import transformers.pipelines because of the following error (look up to see its traceback):
No module named 'tree'

Please note that I have already installed the required packages using the command:

!pip install -r requirements.txt

I am running the script in Jupyter Notebook.

Book Natural Language Processing mit Transformatoren (Deutsch)

training_args = TrainingArguments(output_dir=model_name,
num_train_epochs=2,
learning_rate=2e-5,
per_device_train_batch_size=batch_size,
per_device_eval_batch_size=batch_size,
weight_decay=0.01,
evaluation_strategy="epoch",
disable_tqdm=False,
logging_steps=logging_steps,
push_to_hub=True,
log_level="error")

I have installed `pip install transformers[torch]` and `pip install accelerate -U, but nevertheless I get an error.
What to do?
In this book are many errors in the notebooks and it is very laborious to work with this book. J. van der List

I am getting this error (which sounds a lot like one what was thought to have been fixed):



FileNotFoundError: Couldn't find file at <link to dropbox file>



WORK-AROUND:



emotions = load_dataset("dair-ai/emotion")

TypeError Traceback (most recent call last)
<ipython-input-92-195b9a5c839d> in <cell line: 1>()
----> 1 print(tokenize(emotions['train'][:2]))

<ipython-input-89-f9c17701f610> in tokenize(batch)
1 def tokenize(batch):
----> 2 return tokenizer(batch(['text'],padding = True,truncation=True))

TypeError: 'dict' object is not callable

trainer = Trainer(model=model, args=training_args,
compute_metrics=compute_metrics,
train_dataset=emotions_encoded["train"],
eval_dataset=emotions_encoded["validation"],
tokenizer=tokenizer)
trainer.train();

This raised the following error:
CalledProcessError Traceback (most recent call last)
/usr/local/lib/python3.10/dist-packages/huggingface_hub/repository.py in clone_from(self, repo_url, token)
668
--> 669 run_subprocess(
670 # 'git lfs clone' is deprecated (will display a warning in the terminal)

8 frames
CalledProcessError: Command '['git', 'lfs', 'clone', 'xxx', '.']' returned non-zero exit status 2.

During handling of the above exception, another exception occurred:

OSError Traceback (most recent call last)
/usr/local/lib/python3.10/dist-packages/huggingface_hub/repository.py in clone_from(self, repo_url, token)
707
708 except subprocess.CalledProcessError as exc:
--> 709 raise EnvironmentError(exc.stderr)
710
711 def git_config_username_and_email(self, git_user: Optional[str] = None, git_email: Optional[str] = None):

OSError: WARNING: 'git lfs clone' is deprecated and will not be updated
with new flags from 'git clone'

'git clone' has been updated in upstream Git to have comparable
speeds to 'git lfs clone'.
Cloning into '.'...
remote: Repository not found
fatal: repository 'xxx' not found
Error(s) during clone:
git clone failed: exit status 128