survey-finetuned-phi-2 / evaluation_results.json
aryashah00's picture
Upload folder using huggingface_hub
a2d86ce verified
{
"overall": {
"bleu": 0.08686920384676926,
"rouge1": 0.42906800078253454,
"rouge2": 0.12980707998477484,
"rougeL": 0.23623155081878097,
"bertscore_f1": 0.8911950623989106,
"survey_quality": 0.8676557602032002,
"length_sim": 0.8843561694984895,
"sentence_count_sim": 0.898611111111111,
"sentiment_sim": 0.82
},
"domain_averages": {
"healthcare": {
"bleu": 0.08878746935466889,
"rouge1": 0.4280607827649788,
"rouge2": 0.11904433270661234,
"rougeL": 0.2283888790524234,
"bertscore_f1": 0.893691611289978,
"survey_quality": 0.8260403903318508,
"length_sim": 0.8281211709955528,
"sentence_count_sim": 0.9,
"sentiment_sim": 0.75
},
"education": {
"bleu": 0.08807118160665914,
"rouge1": 0.4106021176696732,
"rouge2": 0.11868045628740853,
"rougeL": 0.22794054600149885,
"bertscore_f1": 0.8927067160606384,
"survey_quality": 0.8724110116469161,
"length_sim": 0.8672330349407481,
"sentence_count_sim": 0.9,
"sentiment_sim": 0.85
},
"consumer_preferences": {
"bleu": 0.07838407903687492,
"rouge1": 0.4261567977628061,
"rouge2": 0.11226322514573846,
"rougeL": 0.22348591672636156,
"bertscore_f1": 0.8893486261367798,
"survey_quality": 0.8223365438379793,
"length_sim": 0.8636762981806043,
"sentence_count_sim": 0.9033333333333335,
"sentiment_sim": 0.7
},
"technology": {
"bleu": 0.07805001669115934,
"rouge1": 0.4103089252031843,
"rouge2": 0.118522466902707,
"rougeL": 0.21950587702302501,
"bertscore_f1": 0.8895265519618988,
"survey_quality": 0.9357964351128644,
"length_sim": 0.9423893053385932,
"sentence_count_sim": 0.915,
"sentiment_sim": 0.95
},
"social_issues": {
"bleu": 0.11316886963111408,
"rouge1": 0.47708421800240125,
"rouge2": 0.17463648108910862,
"rougeL": 0.26958247900476295,
"bertscore_f1": 0.8993694186210632,
"survey_quality": 0.886125911564282,
"length_sim": 0.8583777346928458,
"sentence_count_sim": 0.9000000000000001,
"sentiment_sim": 0.9
},
"environment": {
"bleu": 0.09808532782845751,
"rouge1": 0.4562343754797714,
"rouge2": 0.14828799573664328,
"rougeL": 0.2499818631950458,
"bertscore_f1": 0.8945507824420929,
"survey_quality": 0.8937887595258918,
"length_sim": 0.9113662785776754,
"sentence_count_sim": 0.9200000000000002,
"sentiment_sim": 0.85
},
"finance": {
"bleu": 0.10120500529314957,
"rouge1": 0.4195114660999698,
"rouge2": 0.13928525421676324,
"rougeL": 0.24953612488234161,
"bertscore_f1": 0.8933484077453613,
"survey_quality": 0.8511733939305142,
"length_sim": 0.908520181791542,
"sentence_count_sim": 0.8950000000000001,
"sentiment_sim": 0.75
},
"work_experience": {
"bleu": 0.11075865716694702,
"rouge1": 0.4513839043916786,
"rouge2": 0.15900729516319817,
"rougeL": 0.24893999182457938,
"bertscore_f1": 0.8955537557601929,
"survey_quality": 0.8579697900994321,
"length_sim": 0.878909370298296,
"sentence_count_sim": 0.8950000000000001,
"sentiment_sim": 0.8
},
"lifestyle": {
"bleu": 0.052531740466565245,
"rouge1": 0.38749472013449715,
"rouge2": 0.10198770796102605,
"rougeL": 0.21344619384050273,
"bertscore_f1": 0.8829411089420318,
"survey_quality": 0.8986102692389648,
"length_sim": 0.9058308077168945,
"sentence_count_sim": 0.89,
"sentiment_sim": 0.9
},
"demographics": {
"bleu": 0.059649691392096915,
"rouge1": 0.4238427003163848,
"rouge2": 0.10635558463854244,
"rougeL": 0.23150763663726823,
"bertscore_f1": 0.880913645029068,
"survey_quality": 0.8323050967433065,
"length_sim": 0.8791375124521418,
"sentence_count_sim": 0.8677777777777778,
"sentiment_sim": 0.75
}
}
}