diff --git a/src/transformers/modeling_outputs.py b/src/transformers/modeling_outputs.py
index f05a6229df9d..26a41fc9d1a5 100644
--- a/src/transformers/modeling_outputs.py
+++ b/src/transformers/modeling_outputs.py
@@ -260,7 +260,7 @@ class MaskedLMOutput(ModelOutput):
 
     Args:
         loss (:obj:`torch.FloatTensor` of shape :obj:`(1,)`, `optional`, returned when :obj:`labels` is provided):
-            Masked languaged modeling (MLM) loss.
+            Masked language modeling (MLM) loss.
         logits (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, config.vocab_size)`):
             Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
         hidden_states (:obj:`tuple(torch.FloatTensor)`, `optional`, returned when ``output_hidden_states=True`` is passed or when ``config.output_hidden_states=True``):
@@ -289,7 +289,7 @@ class Seq2SeqLMOutput(ModelOutput):
 
     Args:
         loss (:obj:`torch.FloatTensor` of shape :obj:`(1,)`, `optional`, returned when :obj:`labels` is provided):
-            Languaged modeling loss.
+            Language modeling loss.
         logits (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, config.vocab_size)`):
             Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
         past_key_values (:obj:`List[torch.FloatTensor]`, `optional`, returned when ``use_cache=True`` is passed or when ``config.use_cache=True``):
diff --git a/src/transformers/modeling_prophetnet.py b/src/transformers/modeling_prophetnet.py
index 57e4e4c6a3b6..417111c409bd 100644
--- a/src/transformers/modeling_prophetnet.py
+++ b/src/transformers/modeling_prophetnet.py
@@ -225,7 +225,7 @@ class ProphetNetSeq2SeqLMOutput(ModelOutput):
 
     Args:
         loss (:obj:`torch.FloatTensor` of shape :obj:`(1,)`, `optional`, returned when :obj:`labels` is provided):
-            Languaged modeling loss.
+            Language modeling loss.
         logits (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, decoder_sequence_length, config.vocab_size)`):
             Prediction scores of the main stream language modeling head (scores for each vocabulary token before
             SoftMax).
@@ -438,7 +438,7 @@ class ProphetNetDecoderLMOutput(ModelOutput):
 
     Args:
         loss (:obj:`torch.FloatTensor` of shape :obj:`(1,)`, `optional`, returned when :obj:`labels` is provided):
-            Languaged modeling loss.
+            Language modeling loss.
         logits (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, decoder_sequence_length, config.vocab_size)`):
             Prediction scores of the main stream language modeling head (scores for each vocabulary token before
             SoftMax).
diff --git a/src/transformers/modeling_t5.py b/src/transformers/modeling_t5.py
index f71acf1492f4..8910be332144 100644
--- a/src/transformers/modeling_t5.py
+++ b/src/transformers/modeling_t5.py
@@ -1124,7 +1124,7 @@ def forward(
             >>> model = T5ForConditionalGeneration.from_pretrained('t5-small', return_dict=True)
 
             >>> input_ids = tokenizer('The <extra_id_0> walks in <extra_id_1> park', return_tensors='pt').input_ids
-            labels = tokenizer('<extra_id_0> cute dog <extra_id_1> the <extra_id_2> </s>', return_tensors='pt').input_ids
+            >>> labels = tokenizer('<extra_id_0> cute dog <extra_id_1> the <extra_id_2> </s>', return_tensors='pt').input_ids
             >>> outputs = model(input_ids=input_ids, labels=labels)
             >>> loss = outputs.loss
             >>> logits = outputs.logits
diff --git a/src/transformers/modeling_tf_outputs.py b/src/transformers/modeling_tf_outputs.py
index ac1fd8f5fb50..9a4deb65b0d5 100644
--- a/src/transformers/modeling_tf_outputs.py
+++ b/src/transformers/modeling_tf_outputs.py
@@ -227,7 +227,7 @@ class TFMaskedLMOutput(ModelOutput):
 
     Args:
         loss (:obj:`tf.Tensor` of shape :obj:`(1,)`, `optional`, returned when :obj:`labels` is provided):
-            Masked languaged modeling (MLM) loss.
+            Masked language modeling (MLM) loss.
         logits (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, config.vocab_size)`):
             Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
         hidden_states (:obj:`tuple(tf.Tensor)`, `optional`, returned when ``output_hidden_states=True`` is passed or when ``config.output_hidden_states=True``):
@@ -256,7 +256,7 @@ class TFSeq2SeqLMOutput(ModelOutput):
 
     Args:
         loss (:obj:`tf.Tensor` of shape :obj:`(1,)`, `optional`, returned when :obj:`labels` is provided):
-            Languaged modeling loss.
+            Language modeling loss.
         logits (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length, config.vocab_size)`):
             Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
         past_key_values (:obj:`List[tf.Tensor]`, `optional`, returned when ``use_cache=True`` is passed or when ``config.use_cache=True``):
diff --git a/src/transformers/modeling_tf_t5.py b/src/transformers/modeling_tf_t5.py
index 827af120f86c..e09f5c733164 100644
--- a/src/transformers/modeling_tf_t5.py
+++ b/src/transformers/modeling_tf_t5.py
@@ -1213,7 +1213,7 @@ def call(
             >>> model = TFT5ForConditionalGeneration.from_pretrained('t5-small')
 
             >>> inputs = tokenizer('The <extra_id_0> walks in <extra_id_1> park', return_tensors='tf').input_ids
-            labels = tokenizer('<extra_id_0> cute dog <extra_id_1> the <extra_id_2> </s>', return_tensors='tf').input_ids
+            >>> labels = tokenizer('<extra_id_0> cute dog <extra_id_1> the <extra_id_2> </s>', return_tensors='tf').input_ids
             >>> outputs = model(inputs, labels=labels)
             >>> loss = outputs.loss
             >>> logits = outputs.logits