From c7b2f1d20ac7b61307a1cef6f432a30e43760ca3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Micha=C5=82=20Koz=C5=82owski?=
 <michalkozlowski936@gmail.com>
Date: Tue, 24 Jan 2023 18:16:44 +0100
Subject: [PATCH] fixing

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

diff --git a/train.py b/train.py
index f37d48a..36e4953 100644
--- a/train.py
+++ b/train.py
@@ -35,8 +35,8 @@ def main(config, hug_token):
     added_tokens = []
 
     dataset = load_dataset(config.dataset_path, split='train', streaming=True)
-    train_dataset = dataset.skip(100)
     validation_dataset = dataset.take(100)
+    train_dataset = dataset.skip(10000)
 
     train_dataset = DonutDataset(
                         train_dataset,