fix #1325

Former-commit-id: 59f2cbbd52d4646fbd1ba83032bf522ecc49a50f
2023-11-01 23:38:49 +08:00
parent dab8f45033
commit 8d52fb46ca
5 changed files with 33 additions and 24 deletions
--- a/src/llmtuner/tuner/core/parser.py
+++ b/src/llmtuner/tuner/core/parser.py
@@ -117,9 +117,6 @@ def get_train_args(
    if finetuning_args.stage == "ppo" and model_args.reward_model is None:
        raise ValueError("Reward model is necessary for PPO training.")

-    if finetuning_args.stage == "ppo" and data_args.streaming:
-        raise ValueError("Streaming mode does not suppport PPO training currently.")
-
    if finetuning_args.stage == "ppo" and model_args.shift_attn:
        raise ValueError("PPO training is incompatible with S^2-Attn.")