skaltenp

/

Llama3.2-3B-Thinking-DPO

like 0

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

How to fix it?