agent2world

/

llama3.1_8b_instruct_full_sft_v1_3_epoch

like 0

Follow

Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback 2

• "transformers.trainer_pt_utils.AcceleratorConfig",
• "accelerate.utils.dataclasses.DeepSpeedPlugin",
• "transformers.trainer_utils.IntervalStrategy",
• "transformers.training_args.OptimizerNames",
• "torch.device",
• "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
• "transformers.trainer_utils.SaveStrategy",
• "accelerate.state.PartialState",
• "accelerate.utils.dataclasses.DistributedType",
• "transformers.integrations.deepspeed.HfDeepSpeedConfig",
• "transformers.trainer_utils.SchedulerType",
• "transformers.trainer_utils.HubStrategy",
• "__builtin__.getattr",
• "torch.bfloat16",
• "llamafactory.hparams.training_args.TrainingArguments"

How to fix it?