Update.

[picoclvr.git] / README.txt

diff --git a/README.txt b/README.txt
index 231d292..d4cb93d 100644 (file)
--- a/README.txt
+++ b/README.txt
@@ -14,4 +14,4 @@ For the arithmetic expressions experiments
 # 352M parameters / 2.5M samples, reaches 99.80% after 12 epochs, the
   learning rate schedule is obviously terrible
 
-./main.py --task=expr --nb_blocks=48 --result_dir=results_expr_48b_d1024_2.5M --dim_model=1024 --nb_train_samples=2500000
+./main.py --task=expr --nb_blocks=48 --dim_model=1024 --nb_train_samples=2500000 --result_dir=results_expr_48b_d1024_2.5M