423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-22 22:02:51 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update supervised.py

Browse Source 
Former-commit-id: c09ad8bab38bc2f151da3a924eba225111af2481
This commit is contained in:
hoshi-hiyouga 2024-06-07 03:42:08 +08:00 committed by GitHub
parent fd7bd911a6
commit e3ef239bc0
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
src/llamafactory/data/processors/supervised.py
View File

@ -179,15 +179,16 @@ def preprocess_packed_supervised_dataset(
packed_input_ids += batch_input_ids[index]
packed_labels += batch_labels[index]
if len(packed_input_ids) <= data_args.cutoff_len:
if len(packed_input_ids) < data_args.cutoff_len:
pad_length = data_args.cutoff_len - len(packed_input_ids)
packed_input_ids += [tokenizer.pad_token_id] * pad_length
packed_labels += [IGNORE_INDEX] * pad_length
else:
raise ValueError("The length of packed example exceeds the cutoff length.")
if len(packed_input_ids) != data_args.cutoff_len:
raise ValueError("The length of packed example should be identical to the cutoff length.")
model_inputs["input_ids"].append(packed_input_ids)
model_inputs["attention_mask"].append([1] * len(packed_input_ids))
model_inputs["attention_mask"].append([1] * data_args.cutoff_len)
model_inputs["labels"].append(packed_labels)
return model_inputs