{ "builder_name": "parquet", "citation": "", "config_name": "default", "dataset_name": "parquet", "dataset_size": 5008753497, "description": "", "download_checksums": { "/work/jijun/long_context_dataset/prod/offline_retrieval_dataset/train/reranked//narrativeqa/narrativeqa_rerank.parquet": { "num_bytes": 2530916504, "checksum": null } }, "download_size": 2530916504, "features": { "id": { "dtype": "string", "_type": "Value" }, "dataset_name": { "dtype": "string", "_type": "Value" }, "chunk_size": { "dtype": "int64", "_type": "Value" }, "top_k_starts_new": { "feature": { "dtype": "int64", "_type": "Value" }, "_type": "List" }, "concatenated_text": { "dtype": "string", "_type": "Value" }, "input_ids": { "feature": { "dtype": "int32", "_type": "Value" }, "_type": "List" }, "labels": { "feature": { "dtype": "int64", "_type": "Value" }, "_type": "List" }, "retrieve_idx": { "feature": { "dtype": "int64", "_type": "Value" }, "_type": "List" }, "length": { "dtype": "int64", "_type": "Value" }, "answer_pos": { "feature": { "dtype": "int64", "_type": "Value" }, "_type": "List" } }, "homepage": "", "license": "", "size_in_bytes": 7539670001, "splits": { "train": { "name": "train", "num_bytes": 5008753497, "num_examples": 38203, "shard_lengths": [ 4000, 4000, 4000, 4000, 4000, 4000, 4000, 4000, 4000, 2203 ], "dataset_name": "parquet" } }, "version": { "version_str": "0.0.0", "major": 0, "minor": 0, "patch": 0 } }