Don't log anything before logging is setup in examples (#12121)

* Don't log anything before logging is setup in examples

* Last example

Author: sgugger

examples/pytorch/language-modeling/run_clm.py

@@ -194,21 +194,6 @@ def main():
     else:
         model_args, data_args, training_args = parser.parse_args_into_dataclasses()
 
-    # Detecting last checkpoint.
-    last_checkpoint = None
-    if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
-        last_checkpoint = get_last_checkpoint(training_args.output_dir)
-        if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
-            raise ValueError(
-                f"Output directory ({training_args.output_dir}) already exists and is not empty. "
-                "Use --overwrite_output_dir to overcome."
-            )
-        elif last_checkpoint is not None and training_args.resume_from_checkpoint is None:
-            logger.info(
-                f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change "
-                "the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
-            )
-
     # Setup logging
     logging.basicConfig(
         format="%(asctime)s - %(levelname)s - %(name)s -   %(message)s",
@@ -229,6 +214,21 @@ def main():
         transformers.utils.logging.enable_explicit_format()
     logger.info(f"Training/evaluation parameters {training_args}")
 
+    # Detecting last checkpoint.
+    last_checkpoint = None
+    if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
+        last_checkpoint = get_last_checkpoint(training_args.output_dir)
+        if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
+            raise ValueError(
+                f"Output directory ({training_args.output_dir}) already exists and is not empty. "
+                "Use --overwrite_output_dir to overcome."
+            )
+        elif last_checkpoint is not None and training_args.resume_from_checkpoint is None:
+            logger.info(
+                f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change "
+                "the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
+            )
+
     # Set seed before initializing model.
     set_seed(training_args.seed)
 

examples/pytorch/language-modeling/run_mlm.py

@@ -190,21 +190,6 @@ def main():
     else:
         model_args, data_args, training_args = parser.parse_args_into_dataclasses()
 
-    # Detecting last checkpoint.
-    last_checkpoint = None
-    if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
-        last_checkpoint = get_last_checkpoint(training_args.output_dir)
-        if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
-            raise ValueError(
-                f"Output directory ({training_args.output_dir}) already exists and is not empty. "
-                "Use --overwrite_output_dir to overcome."
-            )
-        elif last_checkpoint is not None and training_args.resume_from_checkpoint is None:
-            logger.info(
-                f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change "
-                "the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
-            )
-
     # Setup logging
     logging.basicConfig(
         format="%(asctime)s - %(levelname)s - %(name)s -   %(message)s",
@@ -225,6 +210,21 @@ def main():
         transformers.utils.logging.enable_explicit_format()
     logger.info(f"Training/evaluation parameters {training_args}")
 
+    # Detecting last checkpoint.
+    last_checkpoint = None
+    if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
+        last_checkpoint = get_last_checkpoint(training_args.output_dir)
+        if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
+            raise ValueError(
+                f"Output directory ({training_args.output_dir}) already exists and is not empty. "
+                "Use --overwrite_output_dir to overcome."
+            )
+        elif last_checkpoint is not None and training_args.resume_from_checkpoint is None:
+            logger.info(
+                f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change "
+                "the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
+            )
+
     # Set seed before initializing model.
     set_seed(training_args.seed)
 

examples/pytorch/language-modeling/run_plm.py

@@ -187,21 +187,6 @@ def main():
     else:
         model_args, data_args, training_args = parser.parse_args_into_dataclasses()
 
-    # Detecting last checkpoint.
-    last_checkpoint = None
-    if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
-        last_checkpoint = get_last_checkpoint(training_args.output_dir)
-        if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
-            raise ValueError(
-                f"Output directory ({training_args.output_dir}) already exists and is not empty. "
-                "Use --overwrite_output_dir to overcome."
-            )
-        elif last_checkpoint is not None and training_args.resume_from_checkpoint is None:
-            logger.info(
-                f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change "
-                "the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
-            )
-
     # Setup logging
     logging.basicConfig(
         format="%(asctime)s - %(levelname)s - %(name)s -   %(message)s",
@@ -222,6 +207,21 @@ def main():
         transformers.utils.logging.enable_explicit_format()
     logger.info(f"Training/evaluation parameters {training_args}")
 
+    # Detecting last checkpoint.
+    last_checkpoint = None
+    if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
+        last_checkpoint = get_last_checkpoint(training_args.output_dir)
+        if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
+            raise ValueError(
+                f"Output directory ({training_args.output_dir}) already exists and is not empty. "
+                "Use --overwrite_output_dir to overcome."
+            )
+        elif last_checkpoint is not None and training_args.resume_from_checkpoint is None:
+            logger.info(
+                f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change "
+                "the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
+            )
+
     # Set seed before initializing model.
     set_seed(training_args.seed)
 

examples/pytorch/multiple-choice/run_swag.py

@@ -214,21 +214,6 @@ def main():
     else:
         model_args, data_args, training_args = parser.parse_args_into_dataclasses()
 
-    # Detecting last checkpoint.
-    last_checkpoint = None
-    if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
-        last_checkpoint = get_last_checkpoint(training_args.output_dir)
-        if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
-            raise ValueError(
-                f"Output directory ({training_args.output_dir}) already exists and is not empty. "
-                "Use --overwrite_output_dir to overcome."
-            )
-        elif last_checkpoint is not None and training_args.resume_from_checkpoint is None:
-            logger.info(
-                f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change "
-                "the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
-            )
-
     # Setup logging
     logging.basicConfig(
         format="%(asctime)s - %(levelname)s - %(name)s -   %(message)s",
@@ -249,6 +234,21 @@ def main():
         transformers.utils.logging.enable_explicit_format()
     logger.info(f"Training/evaluation parameters {training_args}")
 
+    # Detecting last checkpoint.
+    last_checkpoint = None
+    if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
+        last_checkpoint = get_last_checkpoint(training_args.output_dir)
+        if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
+            raise ValueError(
+                f"Output directory ({training_args.output_dir}) already exists and is not empty. "
+                "Use --overwrite_output_dir to overcome."
+            )
+        elif last_checkpoint is not None and training_args.resume_from_checkpoint is None:
+            logger.info(
+                f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change "
+                "the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
+            )
+
     # Set seed before initializing model.
     set_seed(training_args.seed)
 

examples/pytorch/question-answering/run_qa.py

@@ -207,21 +207,6 @@ def main():
     else:
         model_args, data_args, training_args = parser.parse_args_into_dataclasses()
 
-    # Detecting last checkpoint.
-    last_checkpoint = None
-    if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
-        last_checkpoint = get_last_checkpoint(training_args.output_dir)
-        if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
-            raise ValueError(
-                f"Output directory ({training_args.output_dir}) already exists and is not empty. "
-                "Use --overwrite_output_dir to overcome."
-            )
-        elif last_checkpoint is not None and training_args.resume_from_checkpoint is None:
-            logger.info(
-                f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change "
-                "the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
-            )
-
     # Setup logging
     logging.basicConfig(
         format="%(asctime)s - %(levelname)s - %(name)s -   %(message)s",
@@ -242,6 +227,21 @@ def main():
         transformers.utils.logging.enable_explicit_format()
     logger.info(f"Training/evaluation parameters {training_args}")
 
+    # Detecting last checkpoint.
+    last_checkpoint = None
+    if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
+        last_checkpoint = get_last_checkpoint(training_args.output_dir)
+        if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
+            raise ValueError(
+                f"Output directory ({training_args.output_dir}) already exists and is not empty. "
+                "Use --overwrite_output_dir to overcome."
+            )
+        elif last_checkpoint is not None and training_args.resume_from_checkpoint is None:
+            logger.info(
+                f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change "
+                "the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
+            )
+
     # Set seed before initializing model.
     set_seed(training_args.seed)
 

examples/pytorch/question-answering/run_qa_beam_search.py

@@ -206,21 +206,6 @@ def main():
     else:
         model_args, data_args, training_args = parser.parse_args_into_dataclasses()
 
-    # Detecting last checkpoint.
-    last_checkpoint = None
-    if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
-        last_checkpoint = get_last_checkpoint(training_args.output_dir)
-        if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
-            raise ValueError(
-                f"Output directory ({training_args.output_dir}) already exists and is not empty. "
-                "Use --overwrite_output_dir to overcome."
-            )
-        elif last_checkpoint is not None and training_args.resume_from_checkpoint is None:
-            logger.info(
-                f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change "
-                "the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
-            )
-
     # Setup logging
     logging.basicConfig(
         format="%(asctime)s - %(levelname)s - %(name)s -   %(message)s",
@@ -241,6 +226,21 @@ def main():
         transformers.utils.logging.enable_explicit_format()
     logger.info(f"Training/evaluation parameters {training_args}")
 
+    # Detecting last checkpoint.
+    last_checkpoint = None
+    if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
+        last_checkpoint = get_last_checkpoint(training_args.output_dir)
+        if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
+            raise ValueError(
+                f"Output directory ({training_args.output_dir}) already exists and is not empty. "
+                "Use --overwrite_output_dir to overcome."
+            )
+        elif last_checkpoint is not None and training_args.resume_from_checkpoint is None:
+            logger.info(
+                f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change "
+                "the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
+            )
+
     # Set seed before initializing model.
     set_seed(training_args.seed)
 

examples/pytorch/summarization/run_summarization.py

@@ -251,6 +251,24 @@ def main():
     else:
         model_args, data_args, training_args = parser.parse_args_into_dataclasses()
 
+    # Setup logging
+    logging.basicConfig(
+        format="%(asctime)s - %(levelname)s - %(name)s -   %(message)s",
+        datefmt="%m/%d/%Y %H:%M:%S",
+        handlers=[logging.StreamHandler(sys.stdout)],
+    )
+    logger.setLevel(logging.INFO if training_args.should_log else logging.WARN)
+
+    # Log on each process the small summary:
+    logger.warning(
+        f"Process rank: {training_args.local_rank}, device: {training_args.device}, n_gpu: {training_args.n_gpu}"
+        + f"distributed training: {bool(training_args.local_rank != -1)}, 16-bits training: {training_args.fp16}"
+    )
+    # Set the verbosity to info of the Transformers logger (on main process only):
+    if training_args.should_log:
+        transformers.utils.logging.set_verbosity_info()
+    logger.info(f"Training/evaluation parameters {training_args}")
+
     if data_args.source_prefix is None and model_args.model_name_or_path in [
         "t5-small",
         "t5-base",
@@ -278,24 +296,6 @@ def main():
                 "the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
             )
 
-    # Setup logging
-    logging.basicConfig(
-        format="%(asctime)s - %(levelname)s - %(name)s -   %(message)s",
-        datefmt="%m/%d/%Y %H:%M:%S",
-        handlers=[logging.StreamHandler(sys.stdout)],
-    )
-    logger.setLevel(logging.INFO if training_args.should_log else logging.WARN)
-
-    # Log on each process the small summary:
-    logger.warning(
-        f"Process rank: {training_args.local_rank}, device: {training_args.device}, n_gpu: {training_args.n_gpu}"
-        + f"distributed training: {bool(training_args.local_rank != -1)}, 16-bits training: {training_args.fp16}"
-    )
-    # Set the verbosity to info of the Transformers logger (on main process only):
-    if training_args.should_log:
-        transformers.utils.logging.set_verbosity_info()
-    logger.info(f"Training/evaluation parameters {training_args}")
-
     # Set seed before initializing model.
     set_seed(training_args.seed)
 

examples/pytorch/text-classification/run_glue.py

@@ -197,21 +197,6 @@ def main():
     else:
         model_args, data_args, training_args = parser.parse_args_into_dataclasses()
 
-    # Detecting last checkpoint.
-    last_checkpoint = None
-    if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
-        last_checkpoint = get_last_checkpoint(training_args.output_dir)
-        if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
-            raise ValueError(
-                f"Output directory ({training_args.output_dir}) already exists and is not empty. "
-                "Use --overwrite_output_dir to overcome."
-            )
-        elif last_checkpoint is not None and training_args.resume_from_checkpoint is None:
-            logger.info(
-                f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change "
-                "the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
-            )
-
     # Setup logging
     logging.basicConfig(
         format="%(asctime)s - %(levelname)s - %(name)s -   %(message)s",
@@ -232,6 +217,21 @@ def main():
         transformers.utils.logging.enable_explicit_format()
     logger.info(f"Training/evaluation parameters {training_args}")
 
+    # Detecting last checkpoint.
+    last_checkpoint = None
+    if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
+        last_checkpoint = get_last_checkpoint(training_args.output_dir)
+        if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
+            raise ValueError(
+                f"Output directory ({training_args.output_dir}) already exists and is not empty. "
+                "Use --overwrite_output_dir to overcome."
+            )
+        elif last_checkpoint is not None and training_args.resume_from_checkpoint is None:
+            logger.info(
+                f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change "
+                "the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
+            )
+
     # Set seed before initializing model.
     set_seed(training_args.seed)