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

* Alias

* Note alias

* Tests and src

* Rest

* Clean

* Change typing?

* Fix tests

* Deprecation versions

docs/source/de/training.md

@@ -128,12 +128,12 @@ Rufen Sie [`~evaluate.compute`] auf `metric` auf, um die Genauigkeit Ihrer Vorhe
 ...     return metric.compute(predictions=predictions, references=labels)
 ```
 
-Wenn Sie Ihre Bewertungsmetriken während der Feinabstimmung überwachen möchten, geben Sie den Parameter `evaluation_strategy` in Ihren Trainingsargumenten an, um die Bewertungsmetrik am Ende jeder Epoche zu ermitteln:
+Wenn Sie Ihre Bewertungsmetriken während der Feinabstimmung überwachen möchten, geben Sie den Parameter `eval_strategy` in Ihren Trainingsargumenten an, um die Bewertungsmetrik am Ende jeder Epoche zu ermitteln:
 
 ```py
 >>> 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/en/model_memory_anatomy.md

@@ -145,7 +145,7 @@ arguments:
 ```py
 default_args = {
     "output_dir": "tmp",
-    "evaluation_strategy": "steps",
+    "eval_strategy": "steps",
     "num_train_epochs": 1,
     "log_level": "error",
     "report_to": "none",

docs/source/en/tasks/asr.md

@@ -270,7 +270,7 @@ At this point, only three steps remain:
 ...     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/en/tasks/audio_classification.md

@@ -221,7 +221,7 @@ At this point, only three steps remain:
 ```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/en/tasks/document_question_answering.md

@@ -399,7 +399,7 @@ In this case the `output_dir` will also be the name of the repo where your model
 ...     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/en/tasks/image_captioning.md

@@ -196,7 +196,7 @@ 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/en/tasks/image_classification.md

@@ -302,7 +302,7 @@ At this point, only three steps remain:
 >>> 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/en/tasks/knowledge_distillation_for_image_classification.md

@@ -112,7 +112,7 @@ training_args = TrainingArguments(
     fp16=True,
     logging_dir=f"{repo_name}/logs",
     logging_strategy="epoch",
-    evaluation_strategy="epoch",
+    eval_strategy="epoch",
     save_strategy="epoch",
     load_best_model_at_end=True,
     metric_for_best_model="accuracy",

docs/source/en/tasks/language_modeling.md

@@ -249,7 +249,7 @@ At this point, only three steps remain:
 ```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/en/tasks/masked_language_modeling.md

@@ -238,7 +238,7 @@ At this point, only three steps remain:
 ```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/en/tasks/multiple_choice.md

@@ -265,7 +265,7 @@ At this point, only three steps remain:
 ```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/en/tasks/question_answering.md

@@ -218,7 +218,7 @@ At this point, only three steps remain:
 ```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/en/tasks/semantic_segmentation.md

@@ -535,7 +535,7 @@ At this point, only three steps remain:
 ...     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/en/tasks/sequence_classification.md

@@ -187,7 +187,7 @@ At this point, only three steps remain:
 ...     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/en/tasks/summarization.md

@@ -202,7 +202,7 @@ At this point, only three steps remain:
 ```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/en/tasks/text-to-speech.md

@@ -477,7 +477,7 @@ only look at the loss:
 ...     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/en/tasks/token_classification.md

@@ -290,7 +290,7 @@ At this point, only three steps remain:
 ...     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/en/tasks/translation.md

@@ -209,7 +209,7 @@ At this point, only three steps remain:
 ```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/en/tasks/video_classification.md

@@ -354,7 +354,7 @@ Most of the training arguments are self-explanatory, but one that is quite impor
 >>> 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/en/trainer.md

@@ -62,7 +62,7 @@ training_args = TrainingArguments(
     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/en/training.md

@@ -128,12 +128,12 @@ Call [`~evaluate.compute`] on `metric` to calculate the accuracy of your predict
 ...     return metric.compute(predictions=predictions, references=labels)
 ```
 
-If you'd like to monitor your evaluation metrics during fine-tuning, specify the `evaluation_strategy` parameter in your training arguments to report the evaluation metric at the end of each epoch:
+If you'd like to monitor your evaluation metrics during fine-tuning, specify the `eval_strategy` parameter in your training arguments to report the evaluation metric at the end of each epoch:
 
 ```py
 >>> 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/es/tasks/asr.md

@@ -260,7 +260,7 @@ En este punto, solo quedan tres pasos:
 ...     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/es/tasks/image_captioning.md

@@ -188,7 +188,7 @@ 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/es/tasks/image_classification.md

@@ -143,7 +143,7 @@ Al llegar a este punto, solo quedan tres pasos:
 >>> training_args = TrainingArguments(
 ...     output_dir="./results",
 ...     per_device_train_batch_size=16,
-...     evaluation_strategy="steps",
+...     eval_strategy="steps",
 ...     num_train_epochs=4,
 ...     fp16=True,
 ...     save_steps=100,

docs/source/es/tasks/language_modeling.md

@@ -232,7 +232,7 @@ A este punto, solo faltan tres pasos:
 ```py
 >>> training_args = TrainingArguments(
 ...     output_dir="./results",
-...     evaluation_strategy="epoch",
+...     eval_strategy="epoch",
 ...     learning_rate=2e-5,
 ...     weight_decay=0.01,
 ... )
@@ -338,7 +338,7 @@ A este punto, solo faltan tres pasos:
 ```py
 >>> training_args = TrainingArguments(
 ...     output_dir="./results",
-...     evaluation_strategy="epoch",
+...     eval_strategy="epoch",
 ...     learning_rate=2e-5,
 ...     num_train_epochs=3,
 ...     weight_decay=0.01,

docs/source/es/tasks/multiple_choice.md

@@ -212,7 +212,7 @@ En este punto, solo quedan tres pasos:
 ```py
 >>> training_args = TrainingArguments(
 ...     output_dir="./results",
-...     evaluation_strategy="epoch",
+...     eval_strategy="epoch",
 ...     learning_rate=5e-5,
 ...     per_device_train_batch_size=16,
 ...     per_device_eval_batch_size=16,

docs/source/es/tasks/question_answering.md

@@ -182,7 +182,7 @@ En este punto, solo quedan tres pasos:
 ```py
 >>> training_args = TrainingArguments(
 ...     output_dir="./results",
-...     evaluation_strategy="epoch",
+...     eval_strategy="epoch",
 ...     learning_rate=2e-5,
 ...     per_device_train_batch_size=16,
 ...     per_device_eval_batch_size=16,

docs/source/es/tasks/summarization.md

@@ -140,7 +140,7 @@ En este punto, solo faltan tres pasos:
 ```py
 >>> training_args = Seq2SeqTrainingArguments(
 ...     output_dir="./results",
-...     evaluation_strategy="epoch",
+...     eval_strategy="epoch",
 ...     learning_rate=2e-5,
 ...     per_device_train_batch_size=16,
 ...     per_device_eval_batch_size=16,

docs/source/es/trainer.md

@@ -60,7 +60,7 @@ training_args = TrainingArguments(
     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/es/training.md

@@ -120,12 +120,12 @@ Define la función `compute` en `metric` para calcular el accuracy de tus predic
 ...     return metric.compute(predictions=predictions, references=labels)
 ```
 
-Si quieres controlar tus métricas de evaluación durante el fine-tuning, especifica el parámetro `evaluation_strategy` en tus argumentos de entrenamiento para que el modelo tenga en cuenta la métrica de evaluación al final de cada época:
+Si quieres controlar tus métricas de evaluación durante el fine-tuning, especifica el parámetro `eval_strategy` en tus argumentos de entrenamiento para que el modelo tenga en cuenta la métrica de evaluación al final de cada época:
 
 ```py
 >>> from transformers import TrainingArguments
 
->>> training_args = TrainingArguments(output_dir="test_trainer", evaluation_strategy="epoch")
+>>> training_args = TrainingArguments(output_dir="test_trainer", eval_strategy="epoch")
 ```
 
 ### Trainer

docs/source/it/migration.md

@@ -167,7 +167,7 @@ Per quanto riguarda la classe `Trainer`:
 - Il metodo `is_world_master` di `Trainer` è deprecato a favore di `is_world_process_zero`.
 
 Per quanto riguarda la classe `TrainingArguments`:
-- L'argomento `evaluate_during_training` di `TrainingArguments` è deprecato a favore di `evaluation_strategy`.
+- L'argomento `evaluate_during_training` di `TrainingArguments` è deprecato a favore di `eval_strategy`.
 
 Per quanto riguarda il modello Transfo-XL:
 - L'attributo di configurazione `tie_weight` di Transfo-XL diventa `tie_words_embeddings`.

docs/source/it/training.md

@@ -121,12 +121,12 @@ Richiama `compute` su `metric` per calcolare l'accuratezza delle tue previsioni.
 ...     return metric.compute(predictions=predictions, references=labels)
 ```
 
-Se preferisci monitorare le tue metriche di valutazione durante il fine-tuning, specifica il parametro `evaluation_strategy` nei tuoi training arguments per restituire le metriche di valutazione ad ogni epoca di addestramento:
+Se preferisci monitorare le tue metriche di valutazione durante il fine-tuning, specifica il parametro `eval_strategy` nei tuoi training arguments per restituire le metriche di valutazione ad ogni epoca di addestramento:
 
 ```py
 >>> 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/ja/model_memory_anatomy.md

@@ -136,7 +136,7 @@ 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/ja/tasks/asr.md

@@ -270,7 +270,7 @@ MInDS-14 データセットのサンプリング レートは 8000kHz です (
 ...     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/ja/tasks/audio_classification.md

@@ -221,7 +221,7 @@ MInDS-14 データセットのサンプリング レートは 8000khz です (
 ```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/ja/tasks/document_question_answering.md

@@ -403,7 +403,7 @@ 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/ja/tasks/image_captioning.md

@@ -194,7 +194,7 @@ 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/ja/tasks/image_classification.md

@@ -308,7 +308,7 @@ 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/ja/tasks/knowledge_distillation_for_image_classification.md

@@ -112,7 +112,7 @@ training_args = TrainingArguments(
     fp16=True,
     logging_dir=f"{repo_name}/logs",
     logging_strategy="epoch",
-    evaluation_strategy="epoch",
+    eval_strategy="epoch",
     save_strategy="epoch",
     load_best_model_at_end=True,
     metric_for_best_model="accuracy",

docs/source/ja/tasks/language_modeling.md

@@ -246,7 +246,7 @@ Apply the `group_texts` function over the entire dataset:
 ```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,