osmarks/nanogpt-experiments
1
0
Fork 0
mirror of https://github.com/osmarks/nanogpt-experiments.git synced 2024-12-18 14:10:28 +00:00
Code Issues Releases Wiki Activity

nanogpt: allow multithreading in load dataset

Browse Source
This commit is contained in:
Oleksandr Kuvshynov 2023-06-16 20:00:17 -04:00
parent 7339b904ef
commit bb7e96754a
1 changed files with 6 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
data/openwebtext/prepare.py
View File

@ -11,8 +11,13 @@ from datasets import load_dataset # huggingface datasets
# good number to use is ~order number of cpu cores // 2
num_proc = 8
# number of workers in load_dataset() call
# best number might be different from num_proc above as it also depends on NW speed.
# it is better than 1 usually though
num_proc_load_dataset = num_proc
# takes 54GB in huggingface .cache dir, about 8M documents (8,013,769)
dataset = load_dataset("openwebtext")
dataset = load_dataset("openwebtext", num_proc=num_proc_load_dataset)
# owt by default only contains the 'train' split, so create a test split
split_dataset = dataset["train"].train_test_split(test_size=0.0005, seed=2357, shuffle=True)