From e00b4ff1de0591d5093407b16e665e5c86028f04 Mon Sep 17 00:00:00 2001 From: thomwolf Date: Wed, 21 Aug 2019 22:22:17 +0200 Subject: [PATCH] fix #1017 --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 4e57de5842..9751c720b8 100644 --- a/README.md +++ b/README.md @@ -393,8 +393,8 @@ for batch in train_data: loss = model(batch) loss.backward() torch.nn.utils.clip_grad_norm_(model.parameters(), max_grad_norm) # Gradient clipping is not in AdamW anymore (so you can use amp without issue) - scheduler.step() optimizer.step() + scheduler.step() optimizer.zero_grad() ```