oss_instruct / dataset_splits /train /dataset_info.json
Luca0867's picture
oss_isntruct
70ce745 verified
{
"builder_name": "json",
"citation": "",
"config_name": "default",
"dataset_name": "json",
"dataset_size": 31726198,
"description": "",
"download_checksums": {
"/content/drive/MyDrive/Speciale/2. Data cleaning/run2/oss_instruct/oss_instruct_cleaned.jsonl": {
"num_bytes": 38130659,
"checksum": null
}
},
"download_size": 38130659,
"features": {
"instruction": {
"dtype": "string",
"_type": "Value"
},
"response": {
"dtype": "string",
"_type": "Value"
},
"_row_id": {
"dtype": "int64",
"_type": "Value"
},
"syntax_valid": {
"dtype": "bool",
"_type": "Value"
},
"exec_valid": {
"dtype": "bool",
"_type": "Value"
},
"exec_error": {
"dtype": "string",
"_type": "Value"
},
"prompt_norm": {
"dtype": "string",
"_type": "Value"
},
"response_norm": {
"dtype": "string",
"_type": "Value"
},
"prompt_exact_match": {
"dtype": "bool",
"_type": "Value"
},
"entry_point_exact_match": {
"dtype": "bool",
"_type": "Value"
},
"solution_exact_match": {
"dtype": "bool",
"_type": "Value"
},
"max_prompt_similarity": {
"dtype": "float64",
"_type": "Value"
},
"max_code_similarity": {
"dtype": "float64",
"_type": "Value"
},
"leakage_flag": {
"dtype": "bool",
"_type": "Value"
},
"text": {
"dtype": "string",
"_type": "Value"
}
},
"homepage": "",
"license": "",
"size_in_bytes": 69856857,
"splits": {
"train": {
"name": "train",
"num_bytes": 31726198,
"num_examples": 19993,
"dataset_name": "json"
}
},
"version": {
"version_str": "0.0.0",
"major": 0,
"minor": 0,
"patch": 0
}
}