aitextgen
aitextgen copied to clipboard
"TypeError: cannot unpack non-iterable NoneType object" and finetuning an existing model
I have the following code:
from aitextgen import aitextgen
from os import environ
from aitextgen.utils import GPT2ConfigCPU
# disable threading/parallelism to silence warnings
environ["TOKENIZERS_PARALLELISM"] = "false"
environ["OMP_NUM_THREADS"] = "1"
# attempt to load a model with CPU config
config = GPT2ConfigCPU()
ai = aitextgen(model='minimaxir/hacker-news', config=config)
# train/finetune the model using a text file
ai.train(train_data='shakespeare.txt')
As described in the comments, my goal is to use an existing model as a base to finetune using my own data set. When I run this code, I get the following output:
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 40000/40000 [00:01<00:00, 30318.62it/s]
GPU available: False, used: False
TPU available: False, using: 0 TPU cores
IPU available: False, using: 0 IPUs
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 40000/40000 [00:01<00:00, 30360.86it/s]
GPU available: False, used: False
TPU available: False, using: 0 TPU cores
IPU available: False, using: 0 IPUs
0%| | 0/5000 [00:00<?, ?it/s]Traceback (most recent call last):
File "<string>", line 1, in <module>
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py", line 116, in spawn_main
exitcode = _main(fd, parent_sentinel)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py", line 125, in _main
prepare(preparation_data)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py", line 236, in prepare
_fixup_main_from_path(data['init_main_from_path'])
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py", line 287, in _fixup_main_from_path
main_content = runpy.run_path(main_path,
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/runpy.py", line 268, in run_path
return _run_module_code(code, init_globals, run_name,
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/runpy.py", line 97, in _run_module_code
_run_code(code, mod_globals, init_globals,
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/Users/malcolmanderson/Documents/Repositories/TriangularFishGPT/gentri_simple.py", line 14, in <module>
ai.train(train_data='shakespeare.txt')
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/aitextgen/aitextgen.py", line 752, in train
trainer.fit(train_model)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 552, in fit
self._run(model)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 917, in _run
self._dispatch()
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 985, in _dispatch
self.accelerator.start_training(self)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pytorch_lightning/accelerators/accelerator.py", line 92, in start_training
self.training_type_plugin.start_training(trainer)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pytorch_lightning/plugins/training_type/training_type_plugin.py", line 161, in start_training
self._results = trainer.run_stage()
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 995, in run_stage
return self._run_train()
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 1044, in _run_train
self.fit_loop.run()
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pytorch_lightning/loops/base.py", line 111, in run
self.advance(*args, **kwargs)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pytorch_lightning/loops/fit_loop.py", line 200, in advance
epoch_output = self.epoch_loop.run(train_dataloader)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pytorch_lightning/loops/base.py", line 111, in run
self.advance(*args, **kwargs)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pytorch_lightning/loops/epoch/training_epoch_loop.py", line 118, in advance
_, (batch, is_last) = next(dataloader_iter)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pytorch_lightning/profiler/base.py", line 104, in profile_iterable
value = next(iterator)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pytorch_lightning/trainer/supporters.py", line 668, in prefetch_iterator
last = next(it)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pytorch_lightning/trainer/supporters.py", line 589, in __next__
return self.request_next_batch(self.loader_iters)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pytorch_lightning/trainer/supporters.py", line 575, in loader_iters
self._loader_iters = self.create_loader_iters(self.loaders)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pytorch_lightning/trainer/supporters.py", line 633, in create_loader_iters
return apply_to_collection(loaders, Iterable, iter, wrong_dtype=(Sequence, Mapping))
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pytorch_lightning/utilities/apply_func.py", line 96, in apply_to_collection
return function(data, *args, **kwargs)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 352, in __iter__
return self._get_iterator()
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 294, in _get_iterator
return _MultiProcessingDataLoaderIter(self)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 801, in __init__
w.start()
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/process.py", line 121, in start
self._popen = self._Popen(self)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/context.py", line 224, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/context.py", line 284, in _Popen
return Popen(process_obj)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/popen_spawn_posix.py", line 32, in __init__
super().__init__(process_obj)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/popen_fork.py", line 19, in __init__
self._launch(process_obj)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/popen_spawn_posix.py", line 42, in _launch
prep_data = spawn.get_preparation_data(process_obj._name)
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py", line 154, in get_preparation_data
_check_not_importing_main()
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/multiprocessing/spawn.py", line 134, in _check_not_importing_main
raise RuntimeError('''
RuntimeError:
An attempt has been made to start a new process before the
current process has finished its bootstrapping phase.
This probably means that you are not using fork to start your
child processes and you have forgotten to use the proper idiom
in the main module:
if __name__ == '__main__':
freeze_support()
...
The "freeze_support()" line can be omitted if the program
is not going to be frozen to produce an executable.
Exception ignored in: <function tqdm.__del__ at 0x1238779d0>
Traceback (most recent call last):
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/tqdm/std.py", line 1138, in __del__
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/tqdm/std.py", line 1285, in close
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/tqdm/std.py", line 1478, in display
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/tqdm/std.py", line 1141, in __str__
File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/tqdm/std.py", line 1436, in format_dict
TypeError: cannot unpack non-iterable NoneType object
As of right now, the program hasn't returned to the shell, but there's also no indication that anything is happening (i.e. there's no other output showing up).
The following code appears to be working, so far:
from aitextgen.TokenDataset import TokenDataset
from aitextgen.tokenizers import train_tokenizer
from aitextgen.utils import GPT2ConfigCPU
from aitextgen import aitextgen
from os import environ
def train():
# The name of the downloaded Shakespeare text for training
file_name = "shakespeare.txt"
# Train a custom BPE Tokenizer on the downloaded text
# This will save one file: `aitextgen.tokenizer.json`, which contains the
# information needed to rebuild the tokenizer.
train_tokenizer(file_name)
tokenizer_file = "aitextgen.tokenizer.json"
# attempt to load a model with CPU config
config = GPT2ConfigCPU()
ai = aitextgen(model='minimaxir/hacker-news', tokenizer_file=tokenizer_file, config=config)
# You can build datasets for training by creating TokenDatasets,
# which automatically processes the dataset with the appropriate size.
data = TokenDataset(file_name, tokenizer_file=tokenizer_file, block_size=64)
# Train the model! It will save pytorch_model.bin periodically and after completion to the `trained_model` folder.
# On a 2020 8-core iMac, this took ~25 minutes to run.
ai.train(data, batch_size=8, num_steps=50000, generate_every=5000, save_every=5000)
if __name__ == "__main__":
# disable threading/parallelism to silence warnings
environ["TOKENIZERS_PARALLELISM"] = "false"
environ["OMP_NUM_THREADS"] = "1"
train()
However, it's difficult to tell if it's using the minimaxir/hacker-news
model as a base, as all of the output so far looks very Shakespeare-y and not at all Hacker News-y; looking at the source code, it doesn't appear that it should be, although that could just be me misreading.