🚨🚨🚨Deprecate `evaluation_strategy` to `eval_strategy`🚨🚨🚨 (#30190)

* Alias

* Note alias

* Tests and src

* Rest

* Clean

* Change typing?

* Fix tests

* Deprecation versions

docs/source/ja/tasks/masked_language_modeling.md

@@ -231,7 +231,7 @@ pip install transformers datasets evaluate
 ```py
 >>> training_args = TrainingArguments(
 ...     output_dir="my_awesome_eli5_mlm_model",
-...     evaluation_strategy="epoch",
+...     eval_strategy="epoch",
 ...     learning_rate=2e-5,
 ...     num_train_epochs=3,
 ...     weight_decay=0.01,

docs/source/ja/tasks/multiple_choice.md

@@ -266,7 +266,7 @@ tokenized_swag = swag.map(preprocess_function, batched=True)
 ```py
 >>> training_args = TrainingArguments(
 ...     output_dir="my_awesome_swag_model",
-...     evaluation_strategy="epoch",
+...     eval_strategy="epoch",
 ...     save_strategy="epoch",
 ...     load_best_model_at_end=True,
 ...     learning_rate=5e-5,

docs/source/ja/tasks/question_answering.md

@@ -220,7 +220,7 @@ pip install transformers datasets evaluate
 ```py
 >>> training_args = TrainingArguments(
 ...     output_dir="my_awesome_qa_model",
-...     evaluation_strategy="epoch",
+...     eval_strategy="epoch",
 ...     learning_rate=2e-5,
 ...     per_device_train_batch_size=16,
 ...     per_device_eval_batch_size=16,

docs/source/ja/tasks/semantic_segmentation.md

@@ -323,7 +323,7 @@ pip install -q datasets transformers evaluate
 ...     per_device_train_batch_size=2,
 ...     per_device_eval_batch_size=2,
 ...     save_total_limit=3,
-...     evaluation_strategy="steps",
+...     eval_strategy="steps",
 ...     save_strategy="steps",
 ...     save_steps=20,
 ...     eval_steps=20,

docs/source/ja/tasks/sequence_classification.md

@@ -324,7 +324,7 @@ pip install -q datasets transformers evaluate
 ...     per_device_train_batch_size=2,
 ...     per_device_eval_batch_size=2,
 ...     save_total_limit=3,
-...     evaluation_strategy="steps",
+...     eval_strategy="steps",
 ...     save_strategy="steps",
 ...     save_steps=20,
 ...     eval_steps=20,

docs/source/ja/tasks/summarization.md

@@ -204,7 +204,7 @@ pip install transformers datasets evaluate rouge_score
 ```py
 >>> training_args = Seq2SeqTrainingArguments(
 ...     output_dir="my_awesome_billsum_model",
-...     evaluation_strategy="epoch",
+...     eval_strategy="epoch",
 ...     learning_rate=2e-5,
 ...     per_device_train_batch_size=16,
 ...     per_device_eval_batch_size=16,

docs/source/ja/tasks/text-to-speech.md

@@ -477,7 +477,7 @@ SpeechT5 では、モデルのデコーダ部分への入力が 2 分の 1 に
 ...     max_steps=4000,
 ...     gradient_checkpointing=True,
 ...     fp16=True,
-...     evaluation_strategy="steps",
+...     eval_strategy="steps",
 ...     per_device_eval_batch_size=2,
 ...     save_steps=1000,
 ...     eval_steps=1000,

docs/source/ja/tasks/token_classification.md

@@ -288,7 +288,7 @@ pip install transformers datasets evaluate seqeval
 ...     per_device_eval_batch_size=16,
 ...     num_train_epochs=2,
 ...     weight_decay=0.01,
-...     evaluation_strategy="epoch",
+...     eval_strategy="epoch",
 ...     save_strategy="epoch",
 ...     load_best_model_at_end=True,
 ...     push_to_hub=True,

docs/source/ja/tasks/translation.md

@@ -208,7 +208,7 @@ pip install transformers datasets evaluate sacrebleu
 ```py
 >>> training_args = Seq2SeqTrainingArguments(
 ...     output_dir="my_awesome_opus_books_model",
-...     evaluation_strategy="epoch",
+...     eval_strategy="epoch",
 ...     learning_rate=2e-5,
 ...     per_device_train_batch_size=16,
 ...     per_device_eval_batch_size=16,

docs/source/ja/tasks/video_classification.md

@@ -360,7 +360,7 @@ You should probably TRAIN this model on a down-stream task to be able to use it
 >>> args = TrainingArguments(
 ...     new_model_name,
 ...     remove_unused_columns=False,
-...     evaluation_strategy="epoch",
+...     eval_strategy="epoch",
 ...     save_strategy="epoch",
 ...     learning_rate=5e-5,
 ...     per_device_train_batch_size=batch_size,

docs/source/ja/training.md

@@ -135,12 +135,12 @@ BERTモデルの事前学習済みのヘッドは破棄され、ランダムに
 ...     return metric.compute(predictions=predictions, references=labels)
 ```
 
-評価メトリクスをファインチューニング中に監視したい場合、トレーニング引数で `evaluation_strategy` パラメータを指定して、各エポックの終了時に評価メトリクスを報告します：
+評価メトリクスをファインチューニング中に監視したい場合、トレーニング引数で `eval_strategy` パラメータを指定して、各エポックの終了時に評価メトリクスを報告します：
 
 ```python
 >>> from transformers import TrainingArguments, Trainer
 
->>> training_args = TrainingArguments(output_dir="test_trainer", evaluation_strategy="epoch")
+>>> training_args = TrainingArguments(output_dir="test_trainer", eval_strategy="epoch")
 ```
 
 ### Trainer

docs/source/ko/model_memory_anatomy.md

@@ -132,7 +132,7 @@ Tue Jan 11 08:58:05 2022
 ```py
 default_args = {
     "output_dir": "tmp",
-    "evaluation_strategy": "steps",
+    "eval_strategy": "steps",
     "num_train_epochs": 1,
     "log_level": "error",
     "report_to": "none",

docs/source/ko/tasks/asr.md

@@ -274,7 +274,7 @@ MInDS-14 데이터 세트의 샘플링 레이트는 8000kHz이므로([데이터
 ...     gradient_checkpointing=True,
 ...     fp16=True,
 ...     group_by_length=True,
-...     evaluation_strategy="steps",
+...     eval_strategy="steps",
 ...     per_device_eval_batch_size=8,
 ...     save_steps=1000,
 ...     eval_steps=1000,

docs/source/ko/tasks/audio_classification.md

@@ -221,7 +221,7 @@ MinDS-14 데이터 세트의 샘플링 속도는 8000khz이므로(이 정보는
 ```py
 >>> training_args = TrainingArguments(
 ...     output_dir="my_awesome_mind_model",
-...     evaluation_strategy="epoch",
+...     eval_strategy="epoch",
 ...     save_strategy="epoch",
 ...     learning_rate=3e-5,
 ...     per_device_train_batch_size=32,

docs/source/ko/tasks/document_question_answering.md

@@ -385,7 +385,7 @@ end_index 18
 ...     num_train_epochs=20,
 ...     save_steps=200,
 ...     logging_steps=50,
-...     evaluation_strategy="steps",
+...     eval_strategy="steps",
 ...     learning_rate=5e-5,
 ...     save_total_limit=2,
 ...     remove_unused_columns=False,

docs/source/ko/tasks/image_captioning.md

@@ -201,7 +201,7 @@ training_args = TrainingArguments(
     per_device_eval_batch_size=32,
     gradient_accumulation_steps=2,
     save_total_limit=3,
-    evaluation_strategy="steps",
+    eval_strategy="steps",
     eval_steps=50,
     save_strategy="steps",
     save_steps=50,

docs/source/ko/tasks/image_classification.md

@@ -301,7 +301,7 @@ food["test"].set_transform(preprocess_val)
 >>> training_args = TrainingArguments(
 ...     output_dir="my_awesome_food_model",
 ...     remove_unused_columns=False,
-...     evaluation_strategy="epoch",
+...     eval_strategy="epoch",
 ...     save_strategy="epoch",
 ...     learning_rate=5e-5,
 ...     per_device_train_batch_size=16,

docs/source/ko/tasks/language_modeling.md

@@ -233,7 +233,7 @@ pip install transformers datasets evaluate
 ```py
 >>> training_args = TrainingArguments(
 ...     output_dir="my_awesome_eli5_clm-model",
-...     evaluation_strategy="epoch",
+...     eval_strategy="epoch",
 ...     learning_rate=2e-5,
 ...     weight_decay=0.01,
 ...     push_to_hub=True,

docs/source/ko/tasks/masked_language_modeling.md

@@ -236,7 +236,7 @@ Hugging Face 계정에 로그인하여 모델을 업로드하고 커뮤니티와
 ```py
 >>> training_args = TrainingArguments(
 ...     output_dir="my_awesome_eli5_mlm_model",
-...     evaluation_strategy="epoch",
+...     eval_strategy="epoch",
 ...     learning_rate=2e-5,
 ...     num_train_epochs=3,
 ...     weight_decay=0.01,

docs/source/ko/tasks/multiple_choice.md

@@ -265,7 +265,7 @@ tokenized_swag = swag.map(preprocess_function, batched=True)
 ```py
 >>> training_args = TrainingArguments(
 ...     output_dir="my_awesome_swag_model",
-...     evaluation_strategy="epoch",
+...     eval_strategy="epoch",
 ...     save_strategy="epoch",
 ...     load_best_model_at_end=True,
 ...     learning_rate=5e-5,