From 67d3fb6e5b46bfb076140663e16a2ab33fc2da98 Mon Sep 17 00:00:00 2001
From: Boris <kotstantinovskiy@gmail.com>
Date: Wed, 10 Jul 2024 21:35:04 +0300
Subject: [PATCH] Update training.md (#716)

Fix to TrainingArguments
TrainingsArguments doesn't exist in the transformers library
---
 docs/training.md | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/docs/training.md b/docs/training.md
index aec8b812b5..78fcd9e757 100644
--- a/docs/training.md
+++ b/docs/training.md
@@ -193,10 +193,12 @@ intended for training adapters. The `Trainer` class should still be used to full
 class, simply initialize it the same way you would initialize the `Trainer` class, e.g.: 
 
 ```python
+from transformers.training_args import TrainingArguments 
+
 model.add_adapter(task_name)
 model.train_adapter(task_name)
 
-trainings_args =  TrainingsArguments(
+training_args =  TrainingArguments(
     learning_rate=1e-4,
     num_train_epochs=6,
 )