tdro-llm

/

s2-tdro-Mistral-7B-v0.1-top70

like 0

Follow

Task-level Distributionally Robust Optimization for Large Language Model-based Dense Retrieval 2

• "transformers.training_args.OptimizerNames",
• "transformers.trainer_utils.SchedulerType",
• "accelerate.state.PartialState",
• "bowdpr.finetune.arguments.RetrieverTrainingArguments",
• "transformers.trainer_utils.IntervalStrategy",
• "accelerate.utils.dataclasses.DistributedType",
• "torch.device",
• "transformers.trainer_pt_utils.AcceleratorConfig",
• "transformers.trainer_utils.HubStrategy"

How to fix it?