Dongwei

/

Qwen-2.5-7B_Base_Math_smalllr

like 2

• "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
• "transformers.integrations.deepspeed.HfDeepSpeedConfig",
• "accelerate.state.PartialState",
• "transformers.trainer_utils.SchedulerType",
• "open_r1.configs.GRPOConfig",
• "transformers.trainer_utils.HubStrategy",
• "transformers.training_args.OptimizerNames",
• "accelerate.utils.dataclasses.DeepSpeedPlugin",
• "accelerate.utils.dataclasses.DistributedType",
• "transformers.trainer_pt_utils.AcceleratorConfig",
• "transformers.trainer_utils.IntervalStrategy",
• "transformers.trainer_utils.SaveStrategy",
• "torch.device",
• "torch.bfloat16"

How to fix it?