promptstat / eval /_cache /cascade_results.json
xxixx1028's picture
Deploy PromptStat — UI shell + MiniCPM4.1-8B + 4-LoRA hybrid (Modal)
dc9f530 verified
Raw
History Blame Contribute Delete
6.68 kB
{
"baseline": {
"_new_calls": 0,
"technique": {
"headline": 0.12970513816185567,
"axis_any": 0.3282188125416949,
"cats": {
"zero_shot_role": [
0.5291833914588411,
{
"tp": 9,
"fp": 7,
"fn": 8,
"tn": 453
},
17
],
"few_shot": [
0.0,
{
"tp": 0,
"fp": 0,
"fn": 7,
"tn": 470
},
7
],
"thought_generation": [
0.0,
{
"tp": 0,
"fp": 2,
"fn": 0,
"tn": 475
},
0
],
"decomposition": [
-0.0075597554196795,
{
"tp": 0,
"fp": 2,
"fn": 17,
"tn": 458
},
17
],
"self_criticism": [
null,
{
"tp": 0,
"fp": 0,
"fn": 0,
"tn": 477
},
0
],
"flipped": [
-0.002803083391738918,
{
"tp": 0,
"fp": 1,
"fn": 2,
"tn": 474
},
2
]
},
"parse_fail": 3
},
"input_quality": {
"headline": 0.09211310491513845,
"axis_any": 0.1846153846153846,
"cats": {
"goal_stated": [
0.09353119536482576,
{
"tp": 31,
"fp": 219,
"fn": 6,
"tn": 221
},
37
],
"specific_specification": [
0.09069501446545114,
{
"tp": 42,
"fp": 6,
"fn": 249,
"tn": 180
},
291
]
},
"parse_fail": 3
},
"interaction": {
"headline": 0.13385383129426917,
"counts": {
"tp": 176,
"fp": 392,
"fn": 30,
"tn": 218
},
"pos": 206,
"n": 816,
"parse_fail": 1
},
"focus": {
"headline": 0.39427812903901904,
"T": 0.55,
"recall": 0.684931506849315
},
"_secs": 70.5
},
"v2": {
"_new_calls": 0,
"technique": {
"headline": 0.29018965857011875,
"axis_any": 0.551405033291953,
"cats": {
"zero_shot_role": [
0.9000069876318915,
{
"tp": 14,
"fp": 0,
"fn": 3,
"tn": 460
},
17
],
"few_shot": [
0.0,
{
"tp": 0,
"fp": 0,
"fn": 7,
"tn": 470
},
7
],
"thought_generation": [
0.0,
{
"tp": 0,
"fp": 1,
"fn": 0,
"tn": 476
},
0
],
"decomposition": [
0.26075164664858347,
{
"tp": 3,
"fp": 2,
"fn": 14,
"tn": 458
},
17
],
"self_criticism": [
null,
{
"tp": 0,
"fp": 0,
"fn": 0,
"tn": 477
},
0
],
"flipped": [
0.0,
{
"tp": 0,
"fp": 0,
"fn": 2,
"tn": 475
},
2
]
},
"parse_fail": 0
},
"input_quality": {
"headline": 0.3971921361556304,
"axis_any": 0.5678643257052781,
"cats": {
"goal_stated": [
0.226437865359231,
{
"tp": 8,
"fp": 14,
"fn": 29,
"tn": 426
},
37
],
"specific_specification": [
0.5679464069520299,
{
"tp": 225,
"fp": 35,
"fn": 66,
"tn": 151
},
291
]
},
"parse_fail": 0
},
"interaction": {
"headline": 0.07623546939015509,
"counts": {
"tp": 32,
"fp": 57,
"fn": 174,
"tn": 553
},
"pos": 206,
"n": 816,
"parse_fail": 0
},
"focus": {
"headline": 0.4046963209425367,
"T": 0.55,
"recall": 0.684931506849315
},
"_secs": 68.0
},
"v3": {
"_new_calls": 0,
"technique": {
"headline": 0.29018965857011875,
"axis_any": 0.551405033291953,
"cats": {
"zero_shot_role": [
0.9000069876318915,
{
"tp": 14,
"fp": 0,
"fn": 3,
"tn": 460
},
17
],
"few_shot": [
0.0,
{
"tp": 0,
"fp": 0,
"fn": 7,
"tn": 470
},
7
],
"thought_generation": [
0.0,
{
"tp": 0,
"fp": 1,
"fn": 0,
"tn": 476
},
0
],
"decomposition": [
0.26075164664858347,
{
"tp": 3,
"fp": 2,
"fn": 14,
"tn": 458
},
17
],
"self_criticism": [
null,
{
"tp": 0,
"fp": 0,
"fn": 0,
"tn": 477
},
0
],
"flipped": [
0.0,
{
"tp": 0,
"fp": 0,
"fn": 2,
"tn": 475
},
2
]
},
"parse_fail": 0
},
"input_quality": {
"headline": 0.36485526886734726,
"axis_any": 0.5401767615340956,
"cats": {
"goal_stated": [
0.1937101132639565,
{
"tp": 31,
"fp": 141,
"fn": 6,
"tn": 299
},
37
],
"specific_specification": [
0.536000424470738,
{
"tp": 213,
"fp": 32,
"fn": 78,
"tn": 154
},
291
]
},
"parse_fail": 4
},
"interaction": {
"headline": 0.3197441320340984,
"counts": {
"tp": 148,
"fp": 199,
"fn": 58,
"tn": 411
},
"pos": 206,
"n": 816,
"parse_fail": 0
},
"focus": {
"headline": 0.4046963209425367,
"T": 0.55,
"recall": 0.684931506849315
},
"_secs": 68.4
},
"v4": {
"_new_calls": 2204,
"technique": {
"headline": 0.1942222178493125,
"axis_any": 0.3235641692271324,
"cats": {
"zero_shot_role": [
0.631597013644554,
{
"tp": 8,
"fp": 0,
"fn": 9,
"tn": 460
},
17
],
"few_shot": [
-0.0036822724881613316,
{
"tp": 0,
"fp": 1,
"fn": 7,
"tn": 469
},
7
],
"thought_generation": [
0.0,
{
"tp": 0,
"fp": 1,
"fn": 0,
"tn": 476
},
0
],
"decomposition": [
0.1489741302408574,
{
"tp": 2,
"fp": 5,
"fn": 15,
"tn": 455
},
17
],
"self_criticism": [
null,
{
"tp": 0,
"fp": 0,
"fn": 0,
"tn": 477
},
0
],
"flipped": [
0.0,
{
"tp": 0,
"fp": 0,
"fn": 2,
"tn": 475
},
2
]
},
"parse_fail": 2
},
"input_quality": {
"headline": 0.19584802394592618,
"axis_any": 0.42787859824780966,
"cats": {
"goal_stated": [
0.1445087236840895,
{
"tp": 34,
"fp": 192,
"fn": 3,
"tn": 248
},
37
],
"specific_specification": [
0.24718732420776285,
{
"tp": 96,
"fp": 7,
"fn": 195,
"tn": 179
},
291
]
},
"parse_fail": 0
},
"interaction": {
"headline": 0.21034110636700612,
"counts": {
"tp": 152,
"fp": 276,
"fn": 54,
"tn": 334
},
"pos": 206,
"n": 816,
"parse_fail": 0
},
"focus": {
"headline": 0.4333764553686933,
"T": 0.5,
"recall": 0.4931506849315068
},
"_secs": 445.8
}
}