diff --git a/docs/source/tasks/asr.mdx b/docs/source/tasks/asr.mdx
index 862c2cd44781..ce9db3c9dd08 100644
--- a/docs/source/tasks/asr.mdx
+++ b/docs/source/tasks/asr.mdx
@@ -171,7 +171,7 @@ Load Wav2Vec2 with [`AutoModelForCTC`]. For `ctc_loss_reduction`, it is often be
 
 <Tip>
 
-If you aren't familiar with fine-tuning a model with the [`Trainer`], take a look at the basic tutorial [here](training#finetune-with-trainer)!
+If you aren't familiar with fine-tuning a model with the [`Trainer`], take a look at the basic tutorial [here](../training#finetune-with-trainer)!
 
 </Tip>
 
diff --git a/docs/source/tasks/audio_classification.mdx b/docs/source/tasks/audio_classification.mdx
index fbdc2b36932c..63c3c7bd6b66 100644
--- a/docs/source/tasks/audio_classification.mdx
+++ b/docs/source/tasks/audio_classification.mdx
@@ -106,7 +106,7 @@ Load Wav2Vec2 with [`AutoModelForAudioClassification`]. Specify the number of la
 
 <Tip>
 
-If you aren't familiar with fine-tuning a model with the [`Trainer`], take a look at the basic tutorial [here](training#finetune-with-trainer)!
+If you aren't familiar with fine-tuning a model with the [`Trainer`], take a look at the basic tutorial [here](../training#finetune-with-trainer)!
 
 </Tip>
 
diff --git a/docs/source/tasks/image_classification.mdx b/docs/source/tasks/image_classification.mdx
index 5be72780896b..ae85493c0150 100644
--- a/docs/source/tasks/image_classification.mdx
+++ b/docs/source/tasks/image_classification.mdx
@@ -126,7 +126,7 @@ Load ViT with [`AutoModelForImageClassification`]. Specify the number of labels,
 
 <Tip>
 
-If you aren't familiar with fine-tuning a model with the [`Trainer`], take a look at the basic tutorial [here](training#finetune-with-trainer)!
+If you aren't familiar with fine-tuning a model with the [`Trainer`], take a look at the basic tutorial [here](../training#finetune-with-trainer)!
 
 </Tip>
 
diff --git a/docs/source/tasks/language_modeling.mdx b/docs/source/tasks/language_modeling.mdx
index 9f6813ac051b..458b4cb3d36e 100644
--- a/docs/source/tasks/language_modeling.mdx
+++ b/docs/source/tasks/language_modeling.mdx
@@ -212,7 +212,7 @@ Load DistilGPT2 with [`AutoModelForCausalLM`]:
 
 <Tip>
 
-If you aren't familiar with fine-tuning a model with the [`Trainer`], take a look at the basic tutorial [here](training#finetune-with-trainer)!
+If you aren't familiar with fine-tuning a model with the [`Trainer`], take a look at the basic tutorial [here](../training#finetune-with-trainer)!
 
 </Tip>
 
@@ -247,7 +247,7 @@ To fine-tune a model in TensorFlow is just as easy, with only a few differences.
 
 <Tip>
 
-If you aren't familiar with fine-tuning a model with Keras, take a look at the basic tutorial [here](training#finetune-with-keras)!
+If you aren't familiar with fine-tuning a model with Keras, take a look at the basic tutorial [here](../training#finetune-with-keras)!
 
 </Tip>
 
@@ -317,7 +317,7 @@ Load DistilRoBERTa with [`AutoModelForMaskedlM`]:
 
 <Tip>
 
-If you aren't familiar with fine-tuning a model with the [`Trainer`], take a look at the basic tutorial [here](training#finetune-with-trainer)!
+If you aren't familiar with fine-tuning a model with the [`Trainer`], take a look at the basic tutorial [here](../training#finetune-with-trainer)!
 
 </Tip>
 
@@ -353,7 +353,7 @@ To fine-tune a model in TensorFlow is just as easy, with only a few differences.
 
 <Tip>
 
-If you aren't familiar with fine-tuning a model with Keras, take a look at the basic tutorial [here](training#finetune-with-keras)!
+If you aren't familiar with fine-tuning a model with Keras, take a look at the basic tutorial [here](../training#finetune-with-keras)!
 
 </Tip>
 
diff --git a/docs/source/tasks/multiple_choice.mdx b/docs/source/tasks/multiple_choice.mdx
index 3e7101ab2922..6b2d08be531b 100644
--- a/docs/source/tasks/multiple_choice.mdx
+++ b/docs/source/tasks/multiple_choice.mdx
@@ -188,7 +188,7 @@ Load BERT with [`AutoModelForMultipleChoice`]:
 
 <Tip>
 
-If you aren't familiar with fine-tuning a model with Trainer, take a look at the basic tutorial [here](training#finetune-with-trainer)!
+If you aren't familiar with fine-tuning a model with Trainer, take a look at the basic tutorial [here](../training#finetune-with-trainer)!
 
 </Tip>
 
@@ -227,7 +227,7 @@ To fine-tune a model in TensorFlow is just as easy, with only a few differences.
 
 <Tip>
 
-If you aren't familiar with fine-tuning a model with Keras, take a look at the basic tutorial [here](training#finetune-with-keras)!
+If you aren't familiar with fine-tuning a model with Keras, take a look at the basic tutorial [here](../training#finetune-with-keras)!
 
 </Tip>
 
diff --git a/docs/source/tasks/question_answering.mdx b/docs/source/tasks/question_answering.mdx
index 4b9ce42efede..1c2160db0e40 100644
--- a/docs/source/tasks/question_answering.mdx
+++ b/docs/source/tasks/question_answering.mdx
@@ -163,7 +163,7 @@ Load DistilBERT with [`AutoModelForQuestionAnswering`]:
 
 <Tip>
 
-If you aren't familiar with fine-tuning a model with the [`Trainer`], take a look at the basic tutorial [here](training#finetune-with-trainer)!
+If you aren't familiar with fine-tuning a model with the [`Trainer`], take a look at the basic tutorial [here](../training#finetune-with-trainer)!
 
 </Tip>
 
@@ -202,7 +202,7 @@ To fine-tune a model in TensorFlow is just as easy, with only a few differences.
 
 <Tip>
 
-If you aren't familiar with fine-tuning a model with Keras, take a look at the basic tutorial [here](training#finetune-with-keras)!
+If you aren't familiar with fine-tuning a model with Keras, take a look at the basic tutorial [here](../training#finetune-with-keras)!
 
 </Tip>
 
diff --git a/docs/source/tasks/sequence_classification.mdx b/docs/source/tasks/sequence_classification.mdx
index 6062a233f2df..63db0d7f6107 100644
--- a/docs/source/tasks/sequence_classification.mdx
+++ b/docs/source/tasks/sequence_classification.mdx
@@ -103,7 +103,7 @@ Load DistilBERT with [`AutoModelForSequenceClassification`] along with the numbe
 
 <Tip>
 
-If you aren't familiar with fine-tuning a model with the [`Trainer`], take a look at the basic tutorial [here](training#finetune-with-trainer)!
+If you aren't familiar with fine-tuning a model with the [`Trainer`], take a look at the basic tutorial [here](../training#finetune-with-trainer)!
 
 </Tip>
 
@@ -147,21 +147,21 @@ To fine-tune a model in TensorFlow is just as easy, with only a few differences.
 
 <Tip>
 
-If you aren't familiar with fine-tuning a model with Keras, take a look at the basic tutorial [here](training#finetune-with-keras)!
+If you aren't familiar with fine-tuning a model with Keras, take a look at the basic tutorial [here](../training#finetune-with-keras)!
 
 </Tip>
 
 Convert your datasets to the `tf.data.Dataset` format with [`to_tf_dataset`](https://huggingface.co/docs/datasets/package_reference/main_classes.html#datasets.Dataset.to_tf_dataset). Specify inputs and labels in `columns`, whether to shuffle the dataset order, batch size, and the data collator:
 
 ```py
->>> tf_train_dataset = tokenized_imdb["train"].to_tf_dataset(
+>>> tf_train_set = tokenized_imdb["train"].to_tf_dataset(
 ...     columns=["attention_mask", "input_ids", "label"],
 ...     shuffle=True,
 ...     batch_size=16,
 ...     collate_fn=data_collator,
 ... )
 
->>> tf_validation_dataset = tokenized_imdb["train"].to_tf_dataset(
+>>> tf_validation_set = tokenized_imdb["test"].to_tf_dataset(
 ...     columns=["attention_mask", "input_ids", "label"],
 ...     shuffle=False,
 ...     batch_size=16,
diff --git a/docs/source/tasks/summarization.mdx b/docs/source/tasks/summarization.mdx
index 0c5bbbad3d95..a5e1bc4e0acc 100644
--- a/docs/source/tasks/summarization.mdx
+++ b/docs/source/tasks/summarization.mdx
@@ -122,7 +122,7 @@ Load T5 with [`AutoModelForSeq2SeqLM`]:
 
 <Tip>
 
-If you aren't familiar with fine-tuning a model with the [`Trainer`], take a look at the basic tutorial [here](training#finetune-with-trainer)!
+If you aren't familiar with fine-tuning a model with the [`Trainer`], take a look at the basic tutorial [here](../training#finetune-with-trainer)!
 
 </Tip>
 
@@ -163,7 +163,7 @@ To fine-tune a model in TensorFlow is just as easy, with only a few differences.
 
 <Tip>
 
-If you aren't familiar with fine-tuning a model with Keras, take a look at the basic tutorial [here](training#finetune-with-keras)!
+If you aren't familiar with fine-tuning a model with Keras, take a look at the basic tutorial [here](../training#finetune-with-keras)!
 
 </Tip>
 
diff --git a/docs/source/tasks/token_classification.mdx b/docs/source/tasks/token_classification.mdx
index 033c52853f5c..37b316e6529c 100644
--- a/docs/source/tasks/token_classification.mdx
+++ b/docs/source/tasks/token_classification.mdx
@@ -163,7 +163,7 @@ Load DistilBERT with [`AutoModelForTokenClassification`] along with the number o
 
 <Tip>
 
-If you aren't familiar with fine-tuning a model with the [`Trainer`], take a look at the basic tutorial [here](training#finetune-with-trainer)!
+If you aren't familiar with fine-tuning a model with the [`Trainer`], take a look at the basic tutorial [here](../training#finetune-with-trainer)!
 
 </Tip>
 
@@ -202,7 +202,7 @@ To fine-tune a model in TensorFlow is just as easy, with only a few differences.
 
 <Tip>
 
-If you aren't familiar with fine-tuning a model with Keras, take a look at the basic tutorial [here](training#finetune-with-keras)!
+If you aren't familiar with fine-tuning a model with Keras, take a look at the basic tutorial [here](../training#finetune-with-keras)!
 
 </Tip>
 
diff --git a/docs/source/tasks/translation.mdx b/docs/source/tasks/translation.mdx
index ee3af67dda4d..d4a2eae424c1 100644
--- a/docs/source/tasks/translation.mdx
+++ b/docs/source/tasks/translation.mdx
@@ -124,7 +124,7 @@ Load T5 with [`AutoModelForSeq2SeqLM`]:
 
 <Tip>
 
-If you aren't familiar with fine-tuning a model with the [`Trainer`], take a look at the basic tutorial [here](training#finetune-with-trainer)!
+If you aren't familiar with fine-tuning a model with the [`Trainer`], take a look at the basic tutorial [here](../training#finetune-with-trainer)!
 
 </Tip>
 
@@ -165,7 +165,7 @@ To fine-tune a model in TensorFlow is just as easy, with only a few differences.
 
 <Tip>
 
-If you aren't familiar with fine-tuning a model with Keras, take a look at the basic tutorial [here](training#finetune-with-keras)!
+If you aren't familiar with fine-tuning a model with Keras, take a look at the basic tutorial [here](../training#finetune-with-keras)!
 
 </Tip>