riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-08-01 02:31:11 +06:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

compute_loss in trainer failing to label shift for PEFT model when label smoothing enabled. (#25044)

Browse Source 
* added PeftModelForCausalLM to MODEL_FOR_CAUSAL_LM_MAPPING_NAMES dict

* check for PEFT model in compute_loss section

---------

Co-authored-by: Nathan Brake <nbrake3@mmm.com>
This commit is contained in:
Nate Brake 2023-07-24 10:53:10 -04:00 committed by GitHub
parent a03d13c83d
commit 3611fc90e0
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/transformers/trainer.py
View File

@ -2677,7 +2677,11 @@ class Trainer:
self._past = outputs[self.args.past_index]
if labels is not None:
if unwrap_model(model)._get_name() in MODEL_FOR_CAUSAL_LM_MAPPING_NAMES.values():
if is_peft_available() and isinstance(model, PeftModel):
model_name = unwrap_model(model.base_model)._get_name()
else:
model_name = unwrap_model(model)._get_name()
if model_name in MODEL_FOR_CAUSAL_LM_MAPPING_NAMES.values():
loss = self.label_smoother(outputs, labels, shift_labels=True)
else:
loss = self.label_smoother(outputs, labels)