Facing issuse

[bhanuash7]

`Loading cached processed dataset at /home/ubuntu/.cache/huggingface/datasets/text/default-d9e9075e91bf4dac/0.0.0/c4a140d10f020282918b5dd1b8a49f0104729c6177f60a6b49ec2a365ec69f34/cache-f6a5c5c3988f607f.arrow
Exception in thread Thread-12 (run_exp):
Traceback (most recent call last):
File "/home/ubuntu/LLaMA-Factory/src/llmtuner/data/loader.py", line 186, in get_dataset
print_function(next(iter(dataset)))
StopIteration

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner
self.run()
File "/usr/lib/python3.10/threading.py", line 953, in run
self._target(*self._args, **self._kwargs)
File "/home/ubuntu/LLaMA-Factory/src/llmtuner/train/tuner.py", line 31, in run_exp
run_sft(model_args, data_args, training_args, finetuning_args, generating_args, callbacks)
File "/home/ubuntu/LLaMA-Factory/src/llmtuner/train/sft/workflow.py", line 32, in run_sft
dataset = get_dataset(tokenizer, model_args, data_args, training_args, stage="sft")
File "/home/ubuntu/LLaMA-Factory/src/llmtuner/data/loader.py", line 188, in get_dataset
raise RuntimeError("Empty dataset!")
RuntimeError: Empty dataset!
`

[hiyouga]

the problem is related to the dataset format

[bhanuash7]

"wiki_demo": {
"file_name": "wiki_demo.txt",
"file_sha1": "e70375e28eda542a90c68213640cc371898ce181",
"columns": {
"prompt": "text"
}

get the issuse for this and wikipedia_en and other my local text files too.

[hiyouga]

this dataset is only used for pre-training

[bhanuash7]

so what happens if we pretrain on top of 7b model. and why cant we supervised fine tune with the above given dataset? im very new to this and try to learn. help me out with as much as information you can.

Thank you hiyouga