diff --git a/dataset/lm_dataset.py b/dataset/lm_dataset.py index 1fa0397..c5fc48e 100644 --- a/dataset/lm_dataset.py +++ b/dataset/lm_dataset.py @@ -159,7 +159,7 @@ class DPODataset(Dataset): if input_ids[end:end + len(self.eos_id)] == self.eos_id: break end += 1 - for j in range(start + 1, min(end + len(self.eos_id) + 1, self.max_length)): + for j in range(start, min(end + len(self.eos_id) + 1, self.max_length)): loss_mask[j] = 1 i = end + len(self.eos_id) if end < len(input_ids) else len(input_ids) else: @@ -202,4 +202,4 @@ class RLAIFDataset(Dataset): } if __name__ == "__main__": - pass \ No newline at end of file + pass