From dda04a1d5cf9f04144e57976bd5a0300b2c9688f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Micha=C5=82=20Koz=C5=82owski?=
 <michalkozlowski936@gmail.com>
Date: Wed, 25 Jan 2023 22:18:39 +0100
Subject: [PATCH] 80% split

---
 train_stream.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/train_stream.py b/train_stream.py
index 95c8fd7..561828d 100644
--- a/train_stream.py
+++ b/train_stream.py
@@ -34,7 +34,7 @@ def main(config, hug_token):
 
     added_tokens = []
 
-    dataset = load_dataset(config.dataset_path)
+    dataset = load_dataset(config.dataset_path, split="train[:80%]")
     dataset = dataset.train_test_split(test_size=0.1)
 
     train_dataset = DonutDataset(