tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

remove keys to incoporate changes for the trl update (#2616)

Browse Source
This commit is contained in:
aitechguy
2025-05-02 20:47:42 +08:00
committed by GitHub
parent bcb59c70e2
commit e4f73bc98e
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 # dpo trainer may incorrectly prepend the bos_token_id to the dpo outputs
if res["chosen_input_ids"][0] == processing_class.bos_token_id: if res["chosen_input_ids"][0] == processing_class.bos_token_id:
res["chosen_input_ids"] = res["chosen_input_ids"][1:] 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: if res["rejected_input_ids"][0] == processing_class.bos_token_id:
res["rejected_input_ids"] = res["rejected_input_ids"][1:] 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 return res