CohenQu

/

Meta-Llama-3-8B-Instruct_Mixture-of-Thoughts-all-4k-with_reasoning

like 0

• "transformers.trainer_utils.IntervalStrategy",
• "accelerate.state.PartialState",
• "accelerate.utils.dataclasses.DistributedType",
• "transformers.trainer_utils.SchedulerType",
• "transformers.trainer_utils.HubStrategy",
• "transformers.trainer_utils.SaveStrategy",
• "torch.device",
• "transformers.training_args.OptimizerNames",
• "trl.trainer.sft_config.SFTConfig",
• "transformers.trainer_pt_utils.AcceleratorConfig"

How to fix it?