LifelongAlignment

/

aifgen-piecewise-preference-shift-0-reward-model

like 0

Follow

Lifelong Alignment of Agents 6

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

How to fix it?