423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-17 12:20:37 +08:00
Code Issues Packages Projects Releases Wiki Activity

support full-parameter PPO

Browse Source 
Former-commit-id: ce78303600
This commit is contained in:
hiyouga
2023-11-16 02:08:04 +08:00
parent 0c1fab84f1
commit f441932bd1
20 changed files with 288 additions and 145 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -51,7 +51,7 @@ def run_rm(
trainer.log_metrics("train", train_result.metrics)
trainer.save_metrics("train", train_result.metrics)
trainer.save_state()
if trainer.is_world_process_zero() and model_args.plot_loss:
if trainer.is_world_process_zero() and finetuning_args.plot_loss:
plot_loss(training_args.output_dir, keys=["loss", "eval_loss"])
# Evaluation