tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

fix(trl): remove access to invalid property

Browse Source
This commit is contained in:
NanoCode012
2025-05-02 15:41:53 +07:00
parent bcb59c70e2
commit fc1900761b
1 changed files with 0 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/axolotl/core/trainers/dpo/trainer.py
View File

@@ -177,12 +177,8 @@ class AxolotlDPOTrainer(RngLoaderMixin, SchedulerMixin, DPOTrainer):
# dpo trainer may incorrectly prepend the bos_token_id to the dpo outputs
if res["chosen_input_ids"][0] == processing_class.bos_token_id:
res["chosen_input_ids"] = res["chosen_input_ids"][1:]
res["chosen_labels"] = res["chosen_labels"][1:]
res["chosen_attention_mask"] = res["chosen_attention_mask"][1:]
if res["rejected_input_ids"][0] == processing_class.bos_token_id:
res["rejected_input_ids"] = res["rejected_input_ids"][1:]
res["rejected_labels"] = res["rejected_labels"][1:]
res["rejected_attention_mask"] = res["rejected_attention_mask"][1:]
return res