ros/LlamaFactory
1
0
Fork 0
mirror of https://github.com/hiyouga/LlamaFactory.git synced 2026-01-31 06:42:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix #1567

Browse Source 
Former-commit-id: 8c01ffe8d277d49a413571e0669f460c8d0802bf
This commit is contained in:
hiyouga
2023-11-20 18:46:36 +08:00
parent ba2be6371d
commit adf2730d1d
5 changed files with 34 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -94,7 +94,7 @@ def run_ppo(
# Training
if training_args.do_train:
ppo_trainer.ppo_train()
ppo_trainer.ppo_train(resume_from_checkpoint=training_args.resume_from_checkpoint)
ppo_trainer.save_model()
ppo_trainer.save_state() # must be called after save_model to have a folder
if ppo_trainer.is_world_process_zero() and finetuning_args.plot_loss: