423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2026-03-12 15:06:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

support layerwise galore

Browse Source 
Former-commit-id: 8664262cde
This commit is contained in:
hiyouga
2024-03-10 00:24:11 +08:00
parent 276def1897
commit 4a4e4b4354
14 changed files with 109 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llmtuner/train/ppo/workflow.py
View File

@@ -64,7 +64,7 @@ def run_ppo(
)
# Create optimizer and scheduler
optimizer = create_custom_optimzer(model, training_args, finetuning_args)
optimizer = create_custom_optimzer(model, dataset, training_args, finetuning_args)
if optimizer is None:
optimizer = AdamW(filter(lambda p: p.requires_grad, model.parameters()), lr=training_args.learning_rate)