423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-10-15 08:08:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

mask_history args verify valid

Browse Source 
Former-commit-id: 2f8388b4f4195d934400ad9267d72e10ca4105a3
This commit is contained in:
“Wzw” 2024-08-08 10:12:01 +08:00
parent d71446e387
commit 6ec64a7e56
2 changed files with 5 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/llamafactory/data/loader.py
View File

@ -206,6 +206,8 @@ def get_dataset(
template = get_template_and_fix_tokenizer(tokenizer, data_args.template, data_args.tool_format)
if data_args.train_on_prompt and template.efficient_eos:
raise ValueError("Current template does not support `train_on_prompt`.")
if stage!="sft" and data_args.mask_history:
raise ValueError("`Train on the last turn only` is only valid for sft training.")
# Load tokenized dataset
if data_args.tokenized_path is not None:

3
src/llamafactory/hparams/data_args.py
View File

@ -141,3 +141,6 @@ class DataArguments:
if self.streaming and self.max_samples is not None:
raise ValueError("`max_samples` is incompatible with `streaming`.")
if self.mask_history and self.train_on_prompt:
raise ValueError("`Train on the last turn only` does not support `train_on_prompt`.")