{"gsm8k":{"description":"State-of-the-art language models can match human performance on many tasks, but \nthey still struggle to robustly perform multi-step mathematical reasoning. To \ndiagnose the failures of current models and support research, we introduce GSM8K,\na dataset of 8.5K high quality linguistically diverse grade school math word problems.\nWe find that even the largest transformer models fail to achieve high test performance, \ndespite the conceptual simplicity of this problem distribution.\n","citation":"@misc{cobbe2021training,\n title={Training Verifiers to Solve Math Word Problems},\n author={Karl Cobbe and Vineet Kosaraju and Mohammad Bavarian and Jacob Hilton and Reiichiro Nakano and Christopher Hesse and John Schulman},\n year={2021},\n eprint={2110.14168},\n archivePrefix={arXiv},\n primaryClass={cs.LG}\n}\n","homepage":"https://github.com/openai/grade-school-math","license":"","features":{"question":{"dtype":"string","id":null,"_type":"Value"},"answer":{"dtype":"string","id":null,"_type":"Value"}},"post_processed":null,"supervised_keys":null,"task_templates":null,"builder_name":"gsm8_k","config_name":"gsm8k","version":{"version_str":"0.0.1","description":null,"major":0,"minor":0,"patch":1},"splits":{"train":{"name":"train","num_bytes":3963202,"num_examples":7473,"dataset_name":"gsm8_k"},"test":{"name":"test","num_bytes":713732,"num_examples":1319,"dataset_name":"gsm8_k"}},"download_checksums":{"https://raw.githubusercontent.com/openai/grade-school-math/master/grade_school_math/data/train.jsonl":{"num_bytes":4166206,"checksum":"17f347dc51477c50d4efb83959dbb7c56297aba886e5544ee2aaed3024813465"},"https://raw.githubusercontent.com/openai/grade-school-math/master/grade_school_math/data/test.jsonl":{"num_bytes":749738,"checksum":"3730d312f6e3440559ace48831e51066acaca737f6eabec99bccb9e4b3c39d14"}},"download_size":4915944,"post_processing_size":null,"dataset_size":4676934,"size_in_bytes":9592878}}
