Corrections to the PeerQA and DeepPlanning scores of WeMM models

#188
by JUNJIE99 - opened
scores/WeMM-Embedding-2B.json CHANGED
@@ -4641,54 +4641,54 @@
4641
  "num_data": 2162
4642
  },
4643
  "PeerQA": {
4644
- "hit@1": 0.25735294117647056,
4645
- "hit@5": 0.5588235294117647,
4646
- "hit@10": 0.7205882352941176,
4647
- "ndcg_linear@1": 0.25735294117647056,
4648
- "ndcg_linear@5": 0.3056998358676784,
4649
- "ndcg_linear@10": 0.3636935775356273,
4650
- "ndcg_exponential@1": 0.25735294117647056,
4651
- "ndcg_exponential@5": 0.3056998358676784,
4652
- "ndcg_exponential@10": 0.3636935775356273,
4653
- "precision@1": 0.25735294117647056,
4654
- "precision@5": 0.13970588235294118,
4655
- "precision@10": 0.1088235294117647,
4656
- "recall@1": 0.1696778711484594,
4657
- "recall@5": 0.35372544122544125,
4658
- "recall@10": 0.4968470255234961,
4659
- "f1@1": 0.18961834733893557,
4660
- "f1@5": 0.18346198327815977,
4661
- "f1@10": 0.1664763022382061,
4662
- "map@1": 0.25735294117647056,
4663
- "map@5": 0.24915441176470582,
4664
- "map@10": 0.27679130680049796,
4665
- "mrr": 0.3924797560900438,
4666
  "num_pred": 136,
4667
  "num_data": 136
4668
  },
4669
  "DeepPlanning": {
4670
- "hit@1": 0.825,
4671
- "hit@5": 0.9833333333333333,
4672
- "hit@10": 0.9916666666666667,
4673
- "ndcg_linear@1": 0.825,
4674
- "ndcg_linear@5": 0.5567904065311103,
4675
- "ndcg_linear@10": 0.6124785543156093,
4676
- "ndcg_exponential@1": 0.825,
4677
- "ndcg_exponential@5": 0.5567904065311103,
4678
- "ndcg_exponential@10": 0.6124785543156093,
4679
- "precision@1": 0.825,
4680
- "precision@5": 0.4033333333333334,
4681
- "precision@10": 0.25666666666666665,
4682
- "recall@1": 0.2013888888888889,
4683
- "recall@5": 0.48208333333333336,
4684
- "recall@10": 0.6068055555555555,
4685
- "f1@1": 0.32075396825396824,
4686
- "f1@5": 0.43290404040404046,
4687
- "f1@10": 0.3561675824175824,
4688
- "map@1": 0.825,
4689
- "map@5": 0.41765509259259254,
4690
- "map@10": 0.45694422398589063,
4691
- "mrr": 0.8927020202020202,
4692
  "num_pred": 120,
4693
  "num_data": 120
4694
  }
 
4641
  "num_data": 2162
4642
  },
4643
  "PeerQA": {
4644
+ "hit@1": 0.17647058823529413,
4645
+ "hit@5": 0.4485294117647059,
4646
+ "hit@10": 0.5882352941176471,
4647
+ "ndcg_linear@1": 0.17647058823529413,
4648
+ "ndcg_linear@5": 0.23276895663820216,
4649
+ "ndcg_linear@10": 0.27997484682365625,
4650
+ "ndcg_exponential@1": 0.17647058823529413,
4651
+ "ndcg_exponential@5": 0.23276895663820216,
4652
+ "ndcg_exponential@10": 0.27997484682365625,
4653
+ "precision@1": 0.17647058823529413,
4654
+ "precision@5": 0.10882352941176471,
4655
+ "precision@10": 0.08676470588235295,
4656
+ "recall@1": 0.10693277310924369,
4657
+ "recall@5": 0.282092172533349,
4658
+ "recall@10": 0.3983701347671936,
4659
+ "f1@1": 0.12221638655462184,
4660
+ "f1@5": 0.1421629636703166,
4661
+ "f1@10": 0.13180131027515188,
4662
+ "map@1": 0.17647058823529413,
4663
+ "map@5": 0.1829248366013072,
4664
+ "map@10": 0.20505423002534348,
4665
+ "mrr": 0.3054171260072222,
4666
  "num_pred": 136,
4667
  "num_data": 136
4668
  },
4669
  "DeepPlanning": {
4670
+ "hit@1": 0.43333333333333335,
4671
+ "hit@5": 0.675,
4672
+ "hit@10": 0.7916666666666666,
4673
+ "ndcg_linear@1": 0.43333333333333335,
4674
+ "ndcg_linear@5": 0.2564718698410821,
4675
+ "ndcg_linear@10": 0.2794053860266381,
4676
+ "ndcg_exponential@1": 0.43333333333333335,
4677
+ "ndcg_exponential@5": 0.2564718698410821,
4678
+ "ndcg_exponential@10": 0.2794053860266381,
4679
+ "precision@1": 0.43333333333333335,
4680
+ "precision@5": 0.17333333333333334,
4681
+ "precision@10": 0.11000000000000001,
4682
+ "recall@1": 0.10722222222222223,
4683
+ "recall@5": 0.21000000000000002,
4684
+ "recall@10": 0.2615277777777778,
4685
+ "f1@1": 0.17043650793650794,
4686
+ "f1@5": 0.1872727272727273,
4687
+ "f1@10": 0.15299068986568984,
4688
+ "map@1": 0.43333333333333335,
4689
+ "map@5": 0.1654884259259259,
4690
+ "map@10": 0.17328565917107586,
4691
+ "mrr": 0.5485158676527203,
4692
  "num_pred": 120,
4693
  "num_data": 120
4694
  }
scores/WeMM-Embedding-4B.json CHANGED
@@ -4641,54 +4641,54 @@
4641
  "num_data": 2162
4642
  },
4643
  "PeerQA": {
4644
- "hit@1": 0.4264705882352941,
4645
- "hit@5": 0.7867647058823529,
4646
- "hit@10": 0.8970588235294118,
4647
- "ndcg_linear@1": 0.4264705882352941,
4648
- "ndcg_linear@5": 0.49166036324392387,
4649
- "ndcg_linear@10": 0.5613224684920904,
4650
- "ndcg_exponential@1": 0.4264705882352941,
4651
- "ndcg_exponential@5": 0.49166036324392387,
4652
- "ndcg_exponential@10": 0.5613224684920904,
4653
- "precision@1": 0.4264705882352941,
4654
- "precision@5": 0.2426470588235294,
4655
- "precision@10": 0.175,
4656
- "recall@1": 0.25797982654600304,
4657
- "recall@5": 0.5360664458090928,
4658
- "recall@10": 0.7153182601712014,
4659
- "f1@1": 0.29488265002970887,
4660
- "f1@5": 0.30301042911337034,
4661
- "f1@10": 0.2613359237527095,
4662
- "map@1": 0.4264705882352941,
4663
- "map@5": 0.41707924836601307,
4664
- "map@10": 0.4563868255635587,
4665
- "mrr": 0.5817403688816208,
4666
  "num_pred": 136,
4667
  "num_data": 136
4668
  },
4669
  "DeepPlanning": {
4670
- "hit@1": 0.7833333333333333,
4671
- "hit@5": 0.9916666666666667,
4672
- "hit@10": 0.9916666666666667,
4673
- "ndcg_linear@1": 0.7833333333333333,
4674
- "ndcg_linear@5": 0.5463660471889663,
4675
- "ndcg_linear@10": 0.6052911382564152,
4676
- "ndcg_exponential@1": 0.7833333333333333,
4677
- "ndcg_exponential@5": 0.5463660471889663,
4678
- "ndcg_exponential@10": 0.6052911382564152,
4679
- "precision@1": 0.7833333333333333,
4680
- "precision@5": 0.4016666666666667,
4681
- "precision@10": 0.26,
4682
- "recall@1": 0.19291666666666665,
4683
- "recall@5": 0.47875,
4684
- "recall@10": 0.6133333333333333,
4685
- "f1@1": 0.3065873015873016,
4686
- "f1@5": 0.4304124579124579,
4687
- "f1@10": 0.3606593406593406,
4688
- "map@1": 0.7833333333333333,
4689
- "map@5": 0.40427314814814813,
4690
- "map@10": 0.4440738536155202,
4691
- "mrr": 0.8680952380952381,
4692
  "num_pred": 120,
4693
  "num_data": 120
4694
  }
 
4641
  "num_data": 2162
4642
  },
4643
  "PeerQA": {
4644
+ "hit@1": 0.3382352941176471,
4645
+ "hit@5": 0.6911764705882353,
4646
+ "hit@10": 0.8235294117647058,
4647
+ "ndcg_linear@1": 0.3382352941176471,
4648
+ "ndcg_linear@5": 0.3966662159789453,
4649
+ "ndcg_linear@10": 0.45757569928093617,
4650
+ "ndcg_exponential@1": 0.3382352941176471,
4651
+ "ndcg_exponential@5": 0.3966662159789453,
4652
+ "ndcg_exponential@10": 0.45757569928093617,
4653
+ "precision@1": 0.3382352941176471,
4654
+ "precision@5": 0.19999999999999998,
4655
+ "precision@10": 0.14632352941176469,
4656
+ "recall@1": 0.1974406108597285,
4657
+ "recall@5": 0.4497044009911657,
4658
+ "recall@10": 0.6056106271179801,
4659
+ "f1@1": 0.2274806892453951,
4660
+ "f1@5": 0.25104984884396647,
4661
+ "f1@10": 0.21872077986161406,
4662
+ "map@1": 0.3382352941176471,
4663
+ "map@5": 0.3241462418300654,
4664
+ "map@10": 0.3535050964830377,
4665
+ "mrr": 0.49090509497394264,
4666
  "num_pred": 136,
4667
  "num_data": 136
4668
  },
4669
  "DeepPlanning": {
4670
+ "hit@1": 0.425,
4671
+ "hit@5": 0.6833333333333333,
4672
+ "hit@10": 0.7833333333333333,
4673
+ "ndcg_linear@1": 0.425,
4674
+ "ndcg_linear@5": 0.25510983388462605,
4675
+ "ndcg_linear@10": 0.28178380314826973,
4676
+ "ndcg_exponential@1": 0.425,
4677
+ "ndcg_exponential@5": 0.25510983388462605,
4678
+ "ndcg_exponential@10": 0.28178380314826973,
4679
+ "precision@1": 0.425,
4680
+ "precision@5": 0.1716666666666667,
4681
+ "precision@10": 0.11250000000000002,
4682
+ "recall@1": 0.10555555555555557,
4683
+ "recall@5": 0.20763888888888887,
4684
+ "recall@10": 0.26652777777777775,
4685
+ "f1@1": 0.16753968253968252,
4686
+ "f1@5": 0.18516414141414145,
4687
+ "f1@10": 0.1562171855921856,
4688
+ "map@1": 0.425,
4689
+ "map@5": 0.1632199074074074,
4690
+ "map@10": 0.17248578042328042,
4691
+ "mrr": 0.551455788715978,
4692
  "num_pred": 120,
4693
  "num_data": 120
4694
  }
scores/WeMM-Embedding-9B.json CHANGED
@@ -4641,54 +4641,54 @@
4641
  "num_data": 2162
4642
  },
4643
  "PeerQA": {
4644
- "hit@1": 0.35294117647058826,
4645
- "hit@5": 0.7279411764705882,
4646
- "hit@10": 0.8823529411764706,
4647
- "ndcg_linear@1": 0.35294117647058826,
4648
- "ndcg_linear@5": 0.4423072306990305,
4649
- "ndcg_linear@10": 0.5185990095536844,
4650
- "ndcg_exponential@1": 0.35294117647058826,
4651
- "ndcg_exponential@5": 0.4423072306990305,
4652
- "ndcg_exponential@10": 0.5185990095536844,
4653
- "precision@1": 0.35294117647058826,
4654
- "precision@5": 0.22058823529411764,
4655
- "precision@10": 0.16544117647058823,
4656
- "recall@1": 0.1996442895339954,
4657
- "recall@5": 0.5144691705353469,
4658
- "recall@10": 0.7027482321599968,
4659
- "f1@1": 0.23500233426704012,
4660
- "f1@5": 0.28073078881902414,
4661
- "f1@10": 0.25037965587602645,
4662
- "map@1": 0.35294117647058826,
4663
- "map@5": 0.3626184640522876,
4664
- "map@10": 0.4060355461629096,
4665
- "mrr": 0.5245513217228319,
4666
  "num_pred": 136,
4667
  "num_data": 136
4668
  },
4669
  "DeepPlanning": {
4670
- "hit@1": 0.7833333333333333,
4671
- "hit@5": 0.975,
4672
- "hit@10": 0.9833333333333333,
4673
- "ndcg_linear@1": 0.7833333333333333,
4674
- "ndcg_linear@5": 0.5427052404485176,
4675
- "ndcg_linear@10": 0.6053325825139879,
4676
- "ndcg_exponential@1": 0.7833333333333333,
4677
- "ndcg_exponential@5": 0.5427052404485176,
4678
- "ndcg_exponential@10": 0.6053325825139879,
4679
- "precision@1": 0.7833333333333333,
4680
- "precision@5": 0.3983333333333334,
4681
- "precision@10": 0.25916666666666666,
4682
- "recall@1": 0.19208333333333333,
4683
- "recall@5": 0.47069444444444447,
4684
- "recall@10": 0.6141666666666666,
4685
- "f1@1": 0.3055952380952381,
4686
- "f1@5": 0.4251557239057239,
4687
- "f1@10": 0.3600167887667887,
4688
- "map@1": 0.7833333333333333,
4689
- "map@5": 0.4029907407407407,
4690
- "map@10": 0.44662384259259263,
4691
- "mrr": 0.8650160256410256,
4692
  "num_pred": 120,
4693
  "num_data": 120
4694
  }
 
4641
  "num_data": 2162
4642
  },
4643
  "PeerQA": {
4644
+ "hit@1": 0.29411764705882354,
4645
+ "hit@5": 0.6397058823529411,
4646
+ "hit@10": 0.75,
4647
+ "ndcg_linear@1": 0.29411764705882354,
4648
+ "ndcg_linear@5": 0.35947348254787254,
4649
+ "ndcg_linear@10": 0.4120516129270667,
4650
+ "ndcg_exponential@1": 0.29411764705882354,
4651
+ "ndcg_exponential@5": 0.35947348254787254,
4652
+ "ndcg_exponential@10": 0.4120516129270667,
4653
+ "precision@1": 0.29411764705882354,
4654
+ "precision@5": 0.18235294117647058,
4655
+ "precision@10": 0.1323529411764706,
4656
+ "recall@1": 0.16018350522026992,
4657
+ "recall@5": 0.412140739162798,
4658
+ "recall@10": 0.5417800949050949,
4659
+ "f1@1": 0.1908846872082166,
4660
+ "f1@5": 0.22816840022722376,
4661
+ "f1@10": 0.1976229966855437,
4662
+ "map@1": 0.29411764705882354,
4663
+ "map@5": 0.28811274509803925,
4664
+ "map@10": 0.31813349645413724,
4665
+ "mrr": 0.44838899055950593,
4666
  "num_pred": 136,
4667
  "num_data": 136
4668
  },
4669
  "DeepPlanning": {
4670
+ "hit@1": 0.43333333333333335,
4671
+ "hit@5": 0.7666666666666667,
4672
+ "hit@10": 0.8,
4673
+ "ndcg_linear@1": 0.43333333333333335,
4674
+ "ndcg_linear@5": 0.2757164424964664,
4675
+ "ndcg_linear@10": 0.29888528182940827,
4676
+ "ndcg_exponential@1": 0.43333333333333335,
4677
+ "ndcg_exponential@5": 0.2757164424964664,
4678
+ "ndcg_exponential@10": 0.29888528182940827,
4679
+ "precision@1": 0.43333333333333335,
4680
+ "precision@5": 0.19333333333333336,
4681
+ "precision@10": 0.12166666666666667,
4682
+ "recall@1": 0.10180555555555555,
4683
+ "recall@5": 0.22722222222222221,
4684
+ "recall@10": 0.28152777777777777,
4685
+ "f1@1": 0.1634126984126984,
4686
+ "f1@5": 0.20586279461279464,
4687
+ "f1@10": 0.16777014652014652,
4688
+ "map@1": 0.43333333333333335,
4689
+ "map@5": 0.17428703703703707,
4690
+ "map@10": 0.18372674162257496,
4691
+ "mrr": 0.5758292083606976,
4692
  "num_pred": 120,
4693
  "num_data": 120
4694
  }