From 7d7ded25ce400388f7e6084ba829de9637e840f7 Mon Sep 17 00:00:00 2001
From: Andrej Karpathy <andrej.karpathy@gmail.com>
Date: Sat, 14 Jan 2023 03:59:53 +0000
Subject: [PATCH] a bit better settings... for a single gpu at least. these
 settings would fry a simple cpu though i think

---
 config/train_shakespeare_char.py | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/config/train_shakespeare_char.py b/config/train_shakespeare_char.py
index d2b6e83..c50e4dd 100644
--- a/config/train_shakespeare_char.py
+++ b/config/train_shakespeare_char.py
@@ -15,13 +15,13 @@ wandb_run_name = 'mini-gpt'
 
 dataset = 'shakespeare_char'
 batch_size = 64
-block_size = 128 # context of up to 128 previous characters
+block_size = 256 # context of up to 128 previous characters
 
 # baby GPT model :)
-n_layer = 4
-n_head = 4
-n_embd = 128
-dropout = 0.0
+n_layer = 6
+n_head = 6
+n_embd = 384
+dropout = 0.2
 
 learning_rate = 1e-3 # with baby networks can afford to go a bit higher
 max_iters = 5000