survey-finetuned-Qwen2-1.5B-Instruct / evaluation_results.json
aryashah00's picture
Upload folder using huggingface_hub
4f3f51c verified
{
"overall": {
"bleu": 0.05275654375730915,
"rouge1": 0.37727203348496025,
"rouge2": 0.09011004047329778,
"rougeL": 0.19121328095566492,
"bertscore_f1": 0.8824752163887024,
"survey_quality": 0.8660027700978875,
"length_sim": 0.8554845007698529,
"sentence_count_sim": 0.8975238095238095,
"sentiment_sim": 0.845
},
"domain_averages": {
"healthcare": {
"bleu": 0.08278851501478116,
"rouge1": 0.4005043857165389,
"rouge2": 0.1115362597739868,
"rougeL": 0.2164473054664416,
"bertscore_f1": 0.8916730463504792,
"survey_quality": 0.8677062252721173,
"length_sim": 0.8531186758163521,
"sentence_count_sim": 0.9,
"sentiment_sim": 0.85
},
"education": {
"bleu": 0.057061328720606416,
"rouge1": 0.3869462495096812,
"rouge2": 0.09393113653414656,
"rougeL": 0.19182890984955442,
"bertscore_f1": 0.8840996205806733,
"survey_quality": 0.9017665372972615,
"length_sim": 0.875299611891785,
"sentence_count_sim": 0.9800000000000001,
"sentiment_sim": 0.85
},
"consumer_preferences": {
"bleu": 0.025998321374036924,
"rouge1": 0.36163090616290855,
"rouge2": 0.06903576545995618,
"rougeL": 0.1753239689907526,
"bertscore_f1": 0.8782970607280731,
"survey_quality": 0.8747942909785064,
"length_sim": 0.8343828729355188,
"sentence_count_sim": 0.9400000000000001,
"sentiment_sim": 0.85
},
"technology": {
"bleu": 0.04539193107730324,
"rouge1": 0.336309539367159,
"rouge2": 0.07194849913558629,
"rougeL": 0.17706271231454823,
"bertscore_f1": 0.879838490486145,
"survey_quality": 0.8853789836438078,
"length_sim": 0.8761369509314239,
"sentence_count_sim": 0.8800000000000001,
"sentiment_sim": 0.9
},
"social_issues": {
"bleu": 0.08706343082548677,
"rouge1": 0.394914765025913,
"rouge2": 0.12099426402190287,
"rougeL": 0.19957527462392202,
"bertscore_f1": 0.8886084616184234,
"survey_quality": 0.8770664550632803,
"length_sim": 0.8311993651898408,
"sentence_count_sim": 0.9000000000000001,
"sentiment_sim": 0.9
},
"environment": {
"bleu": 0.05820420304219178,
"rouge1": 0.41346435256660463,
"rouge2": 0.09966136010607143,
"rougeL": 0.20441345542748665,
"bertscore_f1": 0.8893770515918732,
"survey_quality": 0.8872793563138085,
"length_sim": 0.8918380689414256,
"sentence_count_sim": 0.9200000000000002,
"sentiment_sim": 0.85
},
"finance": {
"bleu": 0.04762523147842516,
"rouge1": 0.34266809042637797,
"rouge2": 0.0846609727025408,
"rougeL": 0.18766667205240217,
"bertscore_f1": 0.881354820728302,
"survey_quality": 0.833849472682949,
"length_sim": 0.8382150847155134,
"sentence_count_sim": 0.8133333333333332,
"sentiment_sim": 0.85
},
"work_experience": {
"bleu": 0.03830386362266525,
"rouge1": 0.3689729628915851,
"rouge2": 0.07666958924062965,
"rougeL": 0.17970219746585248,
"bertscore_f1": 0.8799687683582306,
"survey_quality": 0.8729311590787017,
"length_sim": 0.8187934772361052,
"sentence_count_sim": 0.9,
"sentiment_sim": 0.9
},
"lifestyle": {
"bleu": 0.03595323988887607,
"rouge1": 0.36774504745517034,
"rouge2": 0.08990097619432927,
"rougeL": 0.19414586068506273,
"bertscore_f1": 0.8763002634048462,
"survey_quality": 0.820093070899232,
"length_sim": 0.8602792126976961,
"sentence_count_sim": 0.85,
"sentiment_sim": 0.75
},
"demographics": {
"bleu": 0.04917537252871874,
"rouge1": 0.39956403572766386,
"rouge2": 0.08276158156382792,
"rougeL": 0.18596645268062634,
"bertscore_f1": 0.875234580039978,
"survey_quality": 0.8391621497492098,
"length_sim": 0.8755816873428678,
"sentence_count_sim": 0.8919047619047618,
"sentiment_sim": 0.75
}
}
}