Lansechen

/

deepseek-v2-lite-16b-chat-R1-Distill-batch8-numinamath

like 1

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

How to fix it?