From 0cf3b3854b2baff9501beffe766e40e6f357c4d6 Mon Sep 17 00:00:00 2001
From: Kalyan Dutia <kalyan.dutia@gmail.com>
Date: Mon, 16 Sep 2024 16:39:09 +0100
Subject: [PATCH] Update src/ml.py

Co-authored-by: Jesse Claven <jesse.claven@me.com>
---
 src/ml.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/ml.py b/src/ml.py
index e5104c6..19ba8a7 100644
--- a/src/ml.py
+++ b/src/ml.py
@@ -116,7 +116,7 @@ def _encode_batch_using_sliding_window(
             if self.get_n_tokens(text) > max_seq_length:
                 windows = sliding_window(
                     text, window_size=max_seq_length, stride=max_seq_length // 2
-                )  # Use max_seq_length as window size and half of it as stride
+                )  # Use reasonable, safe, calculated values for the sliding window
                 processed_texts.extend(windows)
                 window_lengths.append(len(windows))
             else: