[Examples] Fixes inconsistency around eval vs val and predict vs test (#11380)

* added changes for uniformity

* modified files

* corrected typo

* fixed qa scripts

* fix typos

* fixed predict typo in qa no trainer

* fixed test file

* reverted trainer changes

* reverted trainer changes in custom exmaples

* updated readme

* added changes in deepspeed test

* added changes for predict and eval

examples/pytorch/language-modeling/run_clm.py

@@ -126,10 +126,10 @@ class DataTrainingArguments:
             "value if set."
         },
     )
-    max_val_samples: Optional[int] = field(
+    max_eval_samples: Optional[int] = field(
         default=None,
         metadata={
-            "help": "For debugging purposes or quicker training, truncate the number of validation examples to this "
+            "help": "For debugging purposes or quicker training, truncate the number of evaluation examples to this "
             "value if set."
         },
     )
@@ -397,8 +397,8 @@ def main():
         if "validation" not in tokenized_datasets:
             raise ValueError("--do_eval requires a validation dataset")
         eval_dataset = lm_datasets["validation"]
-        if data_args.max_val_samples is not None:
-            eval_dataset = eval_dataset.select(range(data_args.max_val_samples))
+        if data_args.max_eval_samples is not None:
+            eval_dataset = eval_dataset.select(range(data_args.max_eval_samples))
 
     # Initialize our Trainer
     trainer = Trainer(
@@ -439,8 +439,8 @@ def main():
 
         metrics = trainer.evaluate()
 
-        max_val_samples = data_args.max_val_samples if data_args.max_val_samples is not None else len(eval_dataset)
-        metrics["eval_samples"] = min(max_val_samples, len(eval_dataset))
+        max_eval_samples = data_args.max_eval_samples if data_args.max_eval_samples is not None else len(eval_dataset)
+        metrics["eval_samples"] = min(max_eval_samples, len(eval_dataset))
         perplexity = math.exp(metrics["eval_loss"])
         metrics["perplexity"] = perplexity
 

examples/pytorch/language-modeling/run_mlm.py

@@ -157,10 +157,10 @@ class DataTrainingArguments:
             "value if set."
         },
     )
-    max_val_samples: Optional[int] = field(
+    max_eval_samples: Optional[int] = field(
         default=None,
         metadata={
-            "help": "For debugging purposes or quicker training, truncate the number of validation examples to this "
+            "help": "For debugging purposes or quicker training, truncate the number of evaluation examples to this "
             "value if set."
         },
     )
@@ -419,8 +419,8 @@ def main():
         if "validation" not in tokenized_datasets:
             raise ValueError("--do_eval requires a validation dataset")
         eval_dataset = tokenized_datasets["validation"]
-        if data_args.max_val_samples is not None:
-            eval_dataset = eval_dataset.select(range(data_args.max_val_samples))
+        if data_args.max_eval_samples is not None:
+            eval_dataset = eval_dataset.select(range(data_args.max_eval_samples))
 
     # Data collator
     # This one will take care of randomly masking the tokens.
@@ -468,8 +468,8 @@ def main():
 
         metrics = trainer.evaluate()
 
-        max_val_samples = data_args.max_val_samples if data_args.max_val_samples is not None else len(eval_dataset)
-        metrics["eval_samples"] = min(max_val_samples, len(eval_dataset))
+        max_eval_samples = data_args.max_eval_samples if data_args.max_eval_samples is not None else len(eval_dataset)
+        metrics["eval_samples"] = min(max_eval_samples, len(eval_dataset))
         perplexity = math.exp(metrics["eval_loss"])
         metrics["perplexity"] = perplexity
 

examples/pytorch/language-modeling/run_plm.py

@@ -154,10 +154,10 @@ class DataTrainingArguments:
             "value if set."
         },
     )
-    max_val_samples: Optional[int] = field(
+    max_eval_samples: Optional[int] = field(
         default=None,
         metadata={
-            "help": "For debugging purposes or quicker training, truncate the number of validation examples to this "
+            "help": "For debugging purposes or quicker training, truncate the number of evaluation examples to this "
             "value if set."
         },
     )
@@ -397,8 +397,8 @@ def main():
         if "validation" not in tokenized_datasets:
             raise ValueError("--do_eval requires a validation dataset")
         eval_dataset = tokenized_datasets["validation"]
-        if data_args.max_val_samples is not None:
-            eval_dataset = eval_dataset.select(range(data_args.max_val_samples))
+        if data_args.max_eval_samples is not None:
+            eval_dataset = eval_dataset.select(range(data_args.max_eval_samples))
 
     # Data collator
     data_collator = DataCollatorForPermutationLanguageModeling(
@@ -444,8 +444,8 @@ def main():
 
         metrics = trainer.evaluate()
 
-        max_val_samples = data_args.max_val_samples if data_args.max_val_samples is not None else len(eval_dataset)
-        metrics["eval_samples"] = min(max_val_samples, len(eval_dataset))
+        max_eval_samples = data_args.max_eval_samples if data_args.max_eval_samples is not None else len(eval_dataset)
+        metrics["eval_samples"] = min(max_eval_samples, len(eval_dataset))
         perplexity = math.exp(metrics["eval_loss"])
         metrics["perplexity"] = perplexity