We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent b537398 commit 0f1ca05Copy full SHA for 0f1ca05
swift/trainers/rlhf_trainer/grpo_trainer.py
@@ -107,7 +107,6 @@ def __init__(self,
107
from swift.trainers.rlhf_arguments import GRPOConfig
108
args: GRPOConfig = kwargs['args']
109
#add tool call
110
- print(args)
111
self.tool_call = tools[args.tool_call]
112
args.tool_call_weight = args.tool_call_weight
113
self.reward_weights = torch.ones(1, dtype=torch.float32) #通过配置
0 commit comments