Apply several ruff SIM rules (#37283)

* Apply ruff SIM118 fix

Signed-off-by: cyy <[email protected]>

* Apply ruff SIM910 fix

Signed-off-by: cyy <[email protected]>

* Apply ruff SIM101 fix

Signed-off-by: cyy <[email protected]>

* Format code

Signed-off-by: cyy <[email protected]>

* More fixes

Signed-off-by: cyy <[email protected]>

---------

Signed-off-by: cyy <[email protected]>

Author: cyyever

examples/flax/image-captioning/run_image_captioning_flax.py

@@ -906,7 +906,7 @@ def decay_mask_fn(params):
         layer_norm_named_params = {
             layer[-2:]
             for layer_norm_name in layer_norm_candidates
-            for layer in flat_params.keys()
+            for layer in flat_params
             if layer_norm_name in "".join(layer).lower()
         }
         flat_mask = {path: (path[-1] != "bias" and path[-2:] not in layer_norm_named_params) for path in flat_params}

examples/flax/language-modeling/run_bart_dlm_flax.py

@@ -530,7 +530,7 @@ def main():
             trust_remote_code=data_args.trust_remote_code,
         )
 
-        if "validation" not in datasets.keys():
+        if "validation" not in datasets:
             datasets["validation"] = load_dataset(
                 data_args.dataset_name,
                 data_args.dataset_config_name,
@@ -567,7 +567,7 @@ def main():
             num_proc=data_args.preprocessing_num_workers,
         )
 
-        if "validation" not in datasets.keys():
+        if "validation" not in datasets:
             datasets["validation"] = load_dataset(
                 extension,
                 data_files=data_files,
@@ -671,7 +671,7 @@ def tokenize_function(examples):
     # max_seq_length.
     def group_texts(examples):
         # Concatenate all texts.
-        concatenated_examples = {k: list(chain(*examples[k])) for k in examples.keys()}
+        concatenated_examples = {k: list(chain(*examples[k])) for k in examples}
         total_length = len(concatenated_examples[list(examples.keys())[0]])
         # We drop the small remainder, we could add padding if the model supported it instead of this drop, you can
         # customize this part to your needs.
@@ -777,7 +777,7 @@ def decay_mask_fn(params):
         layer_norm_named_params = {
             layer[-2:]
             for layer_norm_name in layer_norm_candidates
-            for layer in flat_params.keys()
+            for layer in flat_params
             if layer_norm_name in "".join(layer).lower()
         }
         flat_mask = {path: (path[-1] != "bias" and path[-2:] not in layer_norm_named_params) for path in flat_params}

examples/flax/language-modeling/run_clm_flax.py

@@ -407,7 +407,7 @@ def main():
             trust_remote_code=model_args.trust_remote_code,
         )
 
-        if "validation" not in dataset.keys():
+        if "validation" not in dataset:
             dataset["validation"] = load_dataset(
                 data_args.dataset_name,
                 data_args.dataset_config_name,
@@ -447,7 +447,7 @@ def main():
             num_proc=data_args.preprocessing_num_workers,
         )
 
-        if "validation" not in dataset.keys():
+        if "validation" not in dataset:
             dataset["validation"] = load_dataset(
                 extension,
                 data_files=data_files,
@@ -580,7 +580,7 @@ def tokenize_function(examples):
     # Main data processing function that will concatenate all texts from our dataset and generate chunks of block_size.
     def group_texts(examples):
         # Concatenate all texts.
-        concatenated_examples = {k: list(chain(*examples[k])) for k in examples.keys()}
+        concatenated_examples = {k: list(chain(*examples[k])) for k in examples}
         total_length = len(concatenated_examples[list(examples.keys())[0]])
         # We drop the small remainder, we could add padding if the model supported it instead of this drop, you can
         # customize this part to your needs.
@@ -674,7 +674,7 @@ def decay_mask_fn(params):
         layer_norm_named_params = {
             layer[-2:]
             for layer_norm_name in layer_norm_candidates
-            for layer in flat_params.keys()
+            for layer in flat_params
             if layer_norm_name in "".join(layer).lower()
         }
         flat_mask = {path: (path[-1] != "bias" and path[-2:] not in layer_norm_named_params) for path in flat_params}

examples/flax/language-modeling/run_mlm_flax.py

@@ -448,7 +448,7 @@ def main():
             trust_remote_code=model_args.trust_remote_code,
         )
 
-        if "validation" not in datasets.keys():
+        if "validation" not in datasets:
             datasets["validation"] = load_dataset(
                 data_args.dataset_name,
                 data_args.dataset_config_name,
@@ -485,7 +485,7 @@ def main():
             num_proc=data_args.preprocessing_num_workers,
         )
 
-        if "validation" not in datasets.keys():
+        if "validation" not in datasets:
             datasets["validation"] = load_dataset(
                 extension,
                 data_files=data_files,
@@ -603,7 +603,7 @@ def tokenize_function(examples):
         # max_seq_length.
         def group_texts(examples):
             # Concatenate all texts.
-            concatenated_examples = {k: list(chain(*examples[k])) for k in examples.keys()}
+            concatenated_examples = {k: list(chain(*examples[k])) for k in examples}
             total_length = len(concatenated_examples[list(examples.keys())[0]])
             # We drop the small remainder, we could add padding if the model supported it instead of this drop, you can
             # customize this part to your needs.
@@ -707,7 +707,7 @@ def decay_mask_fn(params):
         layer_norm_named_params = {
             layer[-2:]
             for layer_norm_name in layer_norm_candidates
-            for layer in flat_params.keys()
+            for layer in flat_params
             if layer_norm_name in "".join(layer).lower()
         }
         flat_mask = {path: (path[-1] != "bias" and path[-2:] not in layer_norm_named_params) for path in flat_params}

examples/flax/language-modeling/run_t5_mlm_flax.py

@@ -572,7 +572,7 @@ def main():
             trust_remote_code=data_args.trust_remote_code,
         )
 
-        if "validation" not in datasets.keys():
+        if "validation" not in datasets:
             datasets["validation"] = load_dataset(
                 data_args.dataset_name,
                 data_args.dataset_config_name,
@@ -609,7 +609,7 @@ def main():
             num_proc=data_args.preprocessing_num_workers,
         )
 
-        if "validation" not in datasets.keys():
+        if "validation" not in datasets:
             datasets["validation"] = load_dataset(
                 extension,
                 data_files=data_files,
@@ -703,7 +703,7 @@ def tokenize_function(examples):
     # Main data processing function that will concatenate all texts from our dataset and generate chunks of expanded_inputs_length.
     def group_texts(examples):
         # Concatenate all texts.
-        concatenated_examples = {k: list(chain(*examples[k])) for k in examples.keys()}
+        concatenated_examples = {k: list(chain(*examples[k])) for k in examples}
         total_length = len(concatenated_examples[list(examples.keys())[0]])
         # We drop the small remainder, we could add padding if the model supported it instead of this drop, you can
         # customize this part to your needs.
@@ -814,7 +814,7 @@ def decay_mask_fn(params):
         layer_norm_named_params = {
             layer[-2:]
             for layer_norm_name in layer_norm_candidates
-            for layer in flat_params.keys()
+            for layer in flat_params
             if layer_norm_name in "".join(layer).lower()
         }
         flat_mask = {path: (path[-1] != "bias" and path[-2:] not in layer_norm_named_params) for path in flat_params}

examples/flax/question-answering/run_qa.py

@@ -345,7 +345,7 @@ def decay_mask_fn(params):
         layer_norm_named_params = {
             layer[-2:]
             for layer_norm_name in layer_norm_candidates
-            for layer in flat_params.keys()
+            for layer in flat_params
             if layer_norm_name in "".join(layer).lower()
         }
         flat_mask = {path: (path[-1] != "bias" and path[-2:] not in layer_norm_named_params) for path in flat_params}

examples/flax/speech-recognition/run_flax_speech_recognition_seq2seq.py

@@ -668,7 +668,7 @@ def decay_mask_fn(params):
         layer_norm_named_params = {
             layer[-2:]
             for layer_norm_name in layer_norm_candidates
-            for layer in flat_params.keys()
+            for layer in flat_params
             if layer_norm_name in "".join(layer).lower()
         }
         flat_mask = {path: (path[-1] != "bias" and path[-2:] not in layer_norm_named_params) for path in flat_params}

examples/flax/summarization/run_summarization_flax.py

@@ -768,7 +768,7 @@ def decay_mask_fn(params):
         layer_norm_named_params = {
             layer[-2:]
             for layer_norm_name in layer_norm_candidates
-            for layer in flat_params.keys()
+            for layer in flat_params
             if layer_norm_name in "".join(layer).lower()
         }
         flat_mask = {path: (path[-1] != "bias" and path[-2:] not in layer_norm_named_params) for path in flat_params}

examples/flax/text-classification/run_flax_glue.py

@@ -249,7 +249,7 @@ def decay_mask_fn(params):
         layer_norm_named_params = {
             layer[-2:]
             for layer_norm_name in layer_norm_candidates
-            for layer in flat_params.keys()
+            for layer in flat_params
             if layer_norm_name in "".join(layer).lower()
         }
         flat_mask = {path: (path[-1] != "bias" and path[-2:] not in layer_norm_named_params) for path in flat_params}

examples/flax/token-classification/run_flax_ner.py

@@ -310,7 +310,7 @@ def decay_mask_fn(params):
         layer_norm_named_params = {
             layer[-2:]
             for layer_norm_name in layer_norm_candidates
-            for layer in flat_params.keys()
+            for layer in flat_params
             if layer_norm_name in "".join(layer).lower()
         }
         flat_mask = {path: (path[-1] != "bias" and path[-2:] not in layer_norm_named_params) for path in flat_params}