gpu-sankhya / gold_metrics_json_float32.json
athrvk's picture
Upload folder using huggingface_hub
d0e38f2 verified
Raw History Blame Contribute Delete
7.34 kB
{
"per_file": {
"tests/gold.jsonl": {
"examples": 227,
"spans": 199,
"precision": 0.955,
"recall": 0.9597989949748744,
"f1": 0.9573934837092732,
"value_acc": 0.9597989949748744,
"categories": {
"digits": {
"spans": 55,
"value_acc": 0.9454545454545454,
"exact_match_rate": 0.9454545454545454
},
"words": {
"spans": 144,
"value_acc": 0.9652777777777778,
"exact_match_rate": 0.9652777777777778
},
"prefix": {
"spans": 52,
"value_acc": 0.9615384615384616,
"exact_match_rate": 0.9615384615384616
},
"range": {
"spans": 17,
"value_acc": 0.8823529411764706,
"exact_match_rate": 0.8823529411764706
},
"currency": {
"spans": 28,
"value_acc": 1.0,
"exact_match_rate": 1.0
},
"multi_unit": {
"spans": 17,
"value_acc": 0.9411764705882353,
"exact_match_rate": 0.9411764705882353
},
"symbol_unit": {
"spans": 19,
"value_acc": 1.0,
"exact_match_rate": 1.0
},
"long": {
"spans": 13,
"value_acc": 0.8461538461538461,
"exact_match_rate": 0.8461538461538461
}
},
"negatives": {
"examples": 37,
"false_positives": 0,
"fp_rate": 0.0
}
},
"tests/gold_deva.jsonl": {
"examples": 186,
"spans": 155,
"precision": 0.9868421052631579,
"recall": 0.967741935483871,
"f1": 0.9771986970684038,
"value_acc": 0.967741935483871,
"categories": {
"digits": {
"spans": 37,
"value_acc": 0.972972972972973,
"exact_match_rate": 0.972972972972973
},
"words": {
"spans": 118,
"value_acc": 0.9661016949152542,
"exact_match_rate": 0.9661016949152542
},
"prefix": {
"spans": 29,
"value_acc": 1.0,
"exact_match_rate": 1.0
},
"range": {
"spans": 13,
"value_acc": 1.0,
"exact_match_rate": 1.0
},
"currency": {
"spans": 20,
"value_acc": 0.9,
"exact_match_rate": 0.9
},
"multi_unit": {
"spans": 10,
"value_acc": 1.0,
"exact_match_rate": 1.0
},
"symbol_unit": {
"spans": 14,
"value_acc": 1.0,
"exact_match_rate": 1.0
},
"mixed_script": {
"spans": 2,
"value_acc": 1.0,
"exact_match_rate": 1.0
},
"long": {
"spans": 2,
"value_acc": 1.0,
"exact_match_rate": 1.0
}
},
"negatives": {
"examples": 38,
"false_positives": 0,
"fp_rate": 0.0
}
},
"tests/gold_mr.jsonl": {
"examples": 173,
"spans": 135,
"precision": 0.9705882352941176,
"recall": 0.9777777777777777,
"f1": 0.974169741697417,
"value_acc": 0.9777777777777777,
"categories": {
"digits": {
"spans": 31,
"value_acc": 1.0,
"exact_match_rate": 1.0
},
"words": {
"spans": 104,
"value_acc": 0.9711538461538461,
"exact_match_rate": 0.9711538461538461
},
"prefix": {
"spans": 23,
"value_acc": 1.0,
"exact_match_rate": 1.0
},
"range": {
"spans": 12,
"value_acc": 1.0,
"exact_match_rate": 1.0
},
"currency": {
"spans": 30,
"value_acc": 1.0,
"exact_match_rate": 1.0
},
"multi_unit": {
"spans": 1,
"value_acc": 1.0,
"exact_match_rate": 1.0
},
"symbol_unit": {
"spans": 9,
"value_acc": 1.0,
"exact_match_rate": 1.0
},
"mixed_script": {
"spans": 1,
"value_acc": 1.0,
"exact_match_rate": 1.0
},
"long": {
"spans": 1,
"value_acc": 1.0,
"exact_match_rate": 1.0
}
},
"negatives": {
"examples": 45,
"false_positives": 0,
"fp_rate": 0.0
}
},
"tests/gold_gu.jsonl": {
"examples": 162,
"spans": 118,
"precision": 0.9658119658119658,
"recall": 0.9576271186440678,
"f1": 0.9617021276595744,
"value_acc": 0.9322033898305084,
"categories": {
"digits": {
"spans": 22,
"value_acc": 1.0,
"exact_match_rate": 1.0
},
"words": {
"spans": 96,
"value_acc": 0.9166666666666666,
"exact_match_rate": 0.9479166666666666
},
"range": {
"spans": 7,
"value_acc": 1.0,
"exact_match_rate": 1.0
},
"currency": {
"spans": 39,
"value_acc": 0.9487179487179487,
"exact_match_rate": 1.0
},
"symbol_unit": {
"spans": 8,
"value_acc": 1.0,
"exact_match_rate": 1.0
}
},
"negatives": {
"examples": 50,
"false_positives": 0,
"fp_rate": 0.0
}
}
},
"combined": {
"examples": 748,
"spans": 607,
"precision": 0.968595041322314,
"recall": 0.9654036243822076,
"f1": 0.9669966996699669,
"value_acc": 0.9604612850082372,
"miss_summary": {
"missed_span": 6,
"spurious_span": 0,
"wrong_value": 3,
"wrong_boundary": 15,
"total": 24
},
"categories": {
"digits": {
"spans": 145,
"value_acc": 0.9724137931034482,
"exact_match_rate": 0.9724137931034482
},
"words": {
"spans": 462,
"value_acc": 0.9567099567099567,
"exact_match_rate": 0.9632034632034632
},
"prefix": {
"spans": 104,
"value_acc": 0.9807692307692307,
"exact_match_rate": 0.9807692307692307
},
"range": {
"spans": 49,
"value_acc": 0.9591836734693877,
"exact_match_rate": 0.9591836734693877
},
"currency": {
"spans": 117,
"value_acc": 0.9658119658119658,
"exact_match_rate": 0.9829059829059829
},
"multi_unit": {
"spans": 28,
"value_acc": 0.9642857142857143,
"exact_match_rate": 0.9642857142857143
},
"symbol_unit": {
"spans": 50,
"value_acc": 1.0,
"exact_match_rate": 1.0
},
"mixed_script": {
"spans": 3,
"value_acc": 1.0,
"exact_match_rate": 1.0
},
"long": {
"spans": 16,
"value_acc": 0.875,
"exact_match_rate": 0.875
}
},
"negatives": {
"examples": 170,
"false_positives": 0,
"fp_rate": 0.0
},
"strict": {
"gold_spans": 607,
"covered": 550,
"coverage": 0.9060955518945635,
"value_correct": 550,
"value_acc": 1.0,
"spurious": 0,
"negatives": {
"examples": 170,
"false_positives": 0,
"fp_rate": 0.0
},
"wrong_value_examples": []
}
}
}