Add an option to reduce compile() console spam (#23938)

* Add an option to reduce compile() console spam

* Add annotations to the example scripts

* Add notes to the quicktour docs as well

* minor fix

examples/tensorflow/contrastive-image-text/run_clip.py

@@ -561,6 +561,8 @@ def main():
             weight_decay_rate=training_args.weight_decay,
             adam_global_clipnorm=training_args.max_grad_norm,
         )
+        # Transformers models compute the right loss for their task by default when labels are passed, and will
+        # use this for training unless you specify your own loss function in compile().
         model.compile(optimizer=optimizer, jit_compile=training_args.xla)
 
         if not training_args.do_eval:

examples/tensorflow/image-classification/run_image_classification.py

@@ -497,6 +497,8 @@ def main():
                 collate_fn=collate_fn,
             ).with_options(dataset_options)
 
+        # Transformers models compute the right loss for their task by default when labels are passed, and will
+        # use this for training unless you specify your own loss function in compile().
         model.compile(optimizer=optimizer, jit_compile=training_args.xla, metrics=["accuracy"])
 
         push_to_hub_model_id = training_args.push_to_hub_model_id

examples/tensorflow/language-modeling-tpu/run_mlm.py

@@ -235,8 +235,10 @@ def main(args):
             num_warmup_steps=total_train_steps // 20,
             init_lr=args.learning_rate,
             weight_decay_rate=args.weight_decay_rate,
-            # TODO Add the other Adam parameters?
         )
+
+        # Transformers models compute the right loss for their task by default when labels are passed, and will
+        # use this for training unless you specify your own loss function in compile().
         model.compile(optimizer=optimizer, metrics=["accuracy"])
 
     def decode_fn(example):

examples/tensorflow/language-modeling/run_clm.py

@@ -537,7 +537,8 @@ def main():
             adam_global_clipnorm=training_args.max_grad_norm,
         )
 
-        # no user-specified loss = will use the model internal loss
+        # Transformers models compute the right loss for their task by default when labels are passed, and will
+        # use this for training unless you specify your own loss function in compile().
         model.compile(optimizer=optimizer, jit_compile=training_args.xla)
         # endregion
 

examples/tensorflow/language-modeling/run_mlm.py

@@ -559,8 +559,9 @@ def main():
             adam_global_clipnorm=training_args.max_grad_norm,
         )
 
-        # no user-specified loss = will use the model internal loss
-        model.compile(optimizer=optimizer, jit_compile=training_args.xla, run_eagerly=True)
+        # Transformers models compute the right loss for their task by default when labels are passed, and will
+        # use this for training unless you specify your own loss function in compile().
+        model.compile(optimizer=optimizer, jit_compile=training_args.xla)
         # endregion
 
         # region Preparing push_to_hub and model card

examples/tensorflow/multiple-choice/run_swag.py

@@ -455,6 +455,8 @@ def main():
             )
         else:
             optimizer = None
+        # Transformers models compute the right loss for their task by default when labels are passed, and will
+        # use this for training unless you specify your own loss function in compile().
         model.compile(optimizer=optimizer, metrics=["accuracy"], jit_compile=training_args.xla)
         # endregion
 

examples/tensorflow/question-answering/run_qa.py

@@ -656,7 +656,8 @@ def main():
                 adam_global_clipnorm=training_args.max_grad_norm,
             )
 
-            # no user-specified loss = will use the model internal loss
+            # Transformers models compute the right loss for their task by default when labels are passed, and will
+            # use this for training unless you specify your own loss function in compile().
             model.compile(optimizer=optimizer, jit_compile=training_args.xla, metrics=["accuracy"])
 
         else:

examples/tensorflow/summarization/run_summarization.py

@@ -674,6 +674,8 @@ def main():
         # endregion
 
         # region Training
+        # Transformers models compute the right loss for their task by default when labels are passed, and will
+        # use this for training unless you specify your own loss function in compile().
         model.compile(optimizer=optimizer, jit_compile=training_args.xla)
         eval_metrics = None
         if training_args.do_train:

examples/tensorflow/text-classification/run_glue.py

@@ -453,6 +453,8 @@ def main():
             metrics = []
         else:
             metrics = ["accuracy"]
+        # Transformers models compute the right loss for their task by default when labels are passed, and will
+        # use this for training unless you specify your own loss function in compile().
         model.compile(optimizer=optimizer, metrics=metrics, jit_compile=training_args.xla)
         # endregion
 

examples/tensorflow/text-classification/run_text_classification.py

@@ -487,6 +487,8 @@ def main():
             metrics = []
         else:
             metrics = ["accuracy"]
+        # Transformers models compute the right loss for their task by default when labels are passed, and will
+        # use this for training unless you specify your own loss function in compile().
         model.compile(optimizer=optimizer, metrics=metrics)
         # endregion
 

examples/tensorflow/token-classification/run_ner.py

@@ -454,7 +454,8 @@ def main():
             weight_decay_rate=training_args.weight_decay,
             adam_global_clipnorm=training_args.max_grad_norm,
         )
-
+        # Transformers models compute the right loss for their task by default when labels are passed, and will
+        # use this for training unless you specify your own loss function in compile().
         model.compile(optimizer=optimizer, jit_compile=training_args.xla)
         # endregion
 

examples/tensorflow/translation/run_translation.py

@@ -643,6 +643,8 @@ def main():
 
         # region Training
         eval_metrics = None
+        # Transformers models compute the right loss for their task by default when labels are passed, and will
+        # use this for training unless you specify your own loss function in compile().
         model.compile(optimizer=optimizer, jit_compile=training_args.xla)
 
         if training_args.do_train: