From 7c8049b2dde68455147c74c6245fc5d44aa03077 Mon Sep 17 00:00:00 2001 From: =?utf8?q?Fran=C3=A7ois=20Fleuret?= Date: Sat, 8 Jul 2023 08:52:56 +0200 Subject: [PATCH] Update. --- README.txt | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/README.txt b/README.txt index bf6180a..231d292 100644 --- a/README.txt +++ b/README.txt @@ -11,6 +11,7 @@ For the arithmetic expressions experiments ./main.py --task=expr -# 352M parameters / 2.5M samples +# 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 --learning_rate_schedule="1:2e-5,3:4e-6" +./main.py --task=expr --nb_blocks=48 --result_dir=results_expr_48b_d1024_2.5M --dim_model=1024 --nb_train_samples=2500000 -- 2.20.1