SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

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

Browse Source 
* 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
This commit is contained in:
Bhadresh Savani
2021-04-26 17:24:31 +01:00
committed by GitHub
parent 7959d83599
commit 1d30ec95c7
19 changed files with 288 additions and 276 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
examples/pytorch/multiple-choice/run_swag.py
View File

@@ -127,10 +127,10 @@ 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."
},
)
@@ -363,8 +363,8 @@ def main():
if "validation" not in datasets:
raise ValueError("--do_eval requires a validation dataset")
eval_dataset = 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))
eval_dataset = eval_dataset.map(
preprocess_function,
batched=True,
@@ -422,8 +422,8 @@ def main():
logger.info("*** Evaluate ***")
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))
trainer.log_metrics("eval", metrics)
trainer.save_metrics("eval", metrics)