CMU-POPE

/

LLaDA-8B-Instruct_Mixture-of-Thoughts-math-256_640_without_reasoning_mbz_1021

like 0

Follow

Privileged On-Policy Exploration 1

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

How to fix it?