| { | |
| "builder_name": "json", | |
| "citation": "", | |
| "config_name": "default", | |
| "dataset_name": "json", | |
| "dataset_size": 2816740545, | |
| "description": "", | |
| "download_checksums": { | |
| "/home/manojale/Documents/Data/commit_data_8m_ready_to_feed.jsonl": { | |
| "num_bytes": 3110715617, | |
| "checksum": null | |
| } | |
| }, | |
| "download_size": 3110715617, | |
| "features": { | |
| "input_ids": { | |
| "feature": { | |
| "dtype": "int32", | |
| "_type": "Value" | |
| }, | |
| "_type": "Sequence" | |
| }, | |
| "attention_mask": { | |
| "feature": { | |
| "dtype": "int8", | |
| "_type": "Value" | |
| }, | |
| "_type": "Sequence" | |
| }, | |
| "word_ids": { | |
| "feature": { | |
| "dtype": "int64", | |
| "_type": "Value" | |
| }, | |
| "_type": "Sequence" | |
| }, | |
| "labels": { | |
| "feature": { | |
| "dtype": "int64", | |
| "_type": "Value" | |
| }, | |
| "_type": "Sequence" | |
| } | |
| }, | |
| "homepage": "", | |
| "license": "", | |
| "size_in_bytes": 5927456162, | |
| "splits": { | |
| "train": { | |
| "name": "train", | |
| "num_bytes": 2816740545, | |
| "num_examples": 8345771, | |
| "shard_lengths": [ | |
| 1461651, | |
| 1509932, | |
| 1500137, | |
| 1478094, | |
| 1517113, | |
| 878844 | |
| ], | |
| "dataset_name": "json" | |
| } | |
| }, | |
| "version": { | |
| "version_str": "0.0.0", | |
| "major": 0, | |
| "minor": 0, | |
| "patch": 0 | |
| } | |
| } |