don't check dataset labels during preprocess for GRPO (#2952) [skip ci]

* don't check dataset labels during preprocess for GRPO

* use enum check per PR feedback
This commit is contained in:
Wing Lian
2025-07-22 20:40:44 -04:00
committed by GitHub
parent 93709eb5ce
commit 5f1a4306b0

View File

@@ -122,7 +122,7 @@ def load_preference_datasets(
math.ceil(len(train_dataset) * cfg.num_epochs / cfg.batch_size)
)
if (cli_args and cli_args.debug) or cfg.debug:
if ((cli_args and cli_args.debug) or cfg.debug) and cfg.rl != RLType.ORPO:
LOG.info("check_dataset_labels...")
num_examples = cli_args.debug_num_examples if cli_args else 1