We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 5521907 commit 2659303Copy full SHA for 2659303
swift/trainers/rlhf_trainer/kto_trainer.py
@@ -37,7 +37,7 @@ def _add_kl_dataset(dataset: LLMDataset, total_batch_size: int, seed: Optional[i
37
'labels': data['labels'],
38
'KL_input_ids': kl_input_ids,
39
'KL_labels': kl_labels,
40
- 'label': kl_data['label']
+ 'label': data['label']
41
})
42
raw_dataset[i:i + total_batch_size] = new_dataset_group
43
i += total_batch_size
0 commit comments