support full-parameter PPO

Former-commit-id: 4af967d69475e1c9fdf1a7983cd6b83bd431abff
2023-11-16 02:08:04 +08:00
parent 8263b2d32d
commit 7a3a0144a5
19 changed files with 280 additions and 140 deletions
--- a/src/llmtuner/train/sft/workflow.py
+++ b/src/llmtuner/train/sft/workflow.py
@@ -69,7 +69,7 @@ def run_sft(
        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