electroglyph commited on
Commit
f7cc039
·
verified ·
1 Parent(s): b32cea2

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +1 -0
  2. 1_Pooling/config.json +10 -0
  3. README.md +49 -0
  4. benchmark.png +3 -0
  5. config.json +25 -0
  6. config_sentence_transformers.json +11 -0
  7. model.safetensors +3 -0
  8. modules.json +20 -0
  9. results/AmazonCounterfactualClassification.json +139 -0
  10. results/ArXivHierarchicalClusteringP2P.json +46 -0
  11. results/ArXivHierarchicalClusteringS2S.json +46 -0
  12. results/ArguAna.json +166 -0
  13. results/AskUbuntuDupQuestions.json +166 -0
  14. results/BIOSSES.json +26 -0
  15. results/Banking77Classification.json +139 -0
  16. results/BiorxivClusteringP2P.v2.json +34 -0
  17. results/CQADupstackGamingRetrieval.json +166 -0
  18. results/CQADupstackUnixRetrieval.json +166 -0
  19. results/ClimateFEVERHardNegatives.json +166 -0
  20. results/FEVERHardNegatives.json +166 -0
  21. results/FiQA2018.json +166 -0
  22. results/HotpotQAHardNegatives.json +166 -0
  23. results/ImdbClassification.json +139 -0
  24. results/MTOPDomainClassification.json +139 -0
  25. results/MassiveIntentClassification.json +139 -0
  26. results/MassiveScenarioClassification.json +139 -0
  27. results/MedrxivClusteringP2P.v2.json +34 -0
  28. results/MedrxivClusteringS2S.v2.json +34 -0
  29. results/MindSmallReranking.json +251 -0
  30. results/SCIDOCS.json +166 -0
  31. results/SICK-R.json +26 -0
  32. results/STS12.json +26 -0
  33. results/STS13.json +26 -0
  34. results/STS14.json +26 -0
  35. results/STS15.json +26 -0
  36. results/STS17.json +26 -0
  37. results/STS22.v2.json +26 -0
  38. results/STSBenchmark.json +26 -0
  39. results/SprintDuplicateQuestions.json +48 -0
  40. results/StackExchangeClustering.v2.json +34 -0
  41. results/StackExchangeClusteringP2P.v2.json +34 -0
  42. results/SummEvalSummarization.v2.json +24 -0
  43. results/TRECCOVID.json +166 -0
  44. results/Touche2020Retrieval.v3.json +166 -0
  45. results/ToxicConversationsClassification.json +139 -0
  46. results/TweetSentimentExtractionClassification.json +139 -0
  47. results/TwentyNewsgroupsClustering.v2.json +34 -0
  48. results/TwitterSemEval2015.json +48 -0
  49. results/TwitterURLCorpus.json +48 -0
  50. results/model_meta.json +1 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ benchmark.png filter=lfs diff=lfs merge=lfs -text
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1024,
3
+ "pooling_mode_cls_token": true,
4
+ "pooling_mode_mean_tokens": false,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ pipeline_tag: sentence-similarity
4
+ tags:
5
+ - sentence-transformers
6
+ - feature-extraction
7
+ - sentence-similarity
8
+ - mteb
9
+ - arctic
10
+ - snowflake-arctic-embed
11
+ - transformers.js
12
+ ---
13
+
14
+ ## arctic-embed-l-tech_and_fiction
15
+
16
+ This is a finetuned version of: [snowflake-arctic-embed-l](https://huggingface.co/Snowflake/snowflake-arctic-embed-l/)
17
+
18
+ It is finetuned on a dataset of ~110K high quality synthetic examples, manually curated and edited.
19
+
20
+ The examples are primarily tech oriented, with some terms from fantasy and sci-fi fiction for good measure.
21
+
22
+
23
+ ## Training Code
24
+
25
+ Code for training this model is here: [train.py](./train.py)
26
+
27
+ Note, this code is for Model A shown below.
28
+
29
+ For this model (Model B below) I trained at rank 128, alpha 128, with a learning rate of around 6e-6 I think, for around 10 epochs.
30
+
31
+
32
+ ## Benchmark Results
33
+
34
+ I've included the results for MTEB benchmark "MTEB(eng, v2)" in the [results](./results/) folder.
35
+
36
+ Here is a screenshot of the results summary (this is Model B):
37
+
38
+ ![benchmark](./benchmark.png)
39
+
40
+
41
+ ## License
42
+
43
+
44
+ arctic-embed-l-tech_and_fiction is licensed under the [Apache-2](https://www.apache.org/licenses/LICENSE-2.0). The released models can be used for commercial purposes free of charge.
45
+
46
+
47
+ ## Acknowledgement
48
+
49
+ Thank you to the Snowflake team for making some excellent models!
benchmark.png ADDED

Git LFS Details

  • SHA256: c3e65032ee01f23ff07fd505e5e64214eba583a94f3d18ee48eb6ba85bb170f0
  • Pointer size: 131 Bytes
  • Size of remote file: 446 kB
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "torch_dtype": "bfloat16",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 1024,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4096,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 24,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "transformers_version": "4.56.2",
21
+ "type_vocab_size": 2,
22
+ "unsloth_version": "2025.12.1",
23
+ "use_cache": true,
24
+ "vocab_size": 30522
25
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.7.0.dev0",
4
+ "transformers": "4.39.3",
5
+ "pytorch": "2.1.0+cu121"
6
+ },
7
+ "prompts": {
8
+ "query": "Represent this sentence for searching relevant passages: "
9
+ },
10
+ "default_prompt_name": null
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a13f16e0ef8060b09fba61a9a1f924c08cbd6b902637e550c85940b338a37df8
3
+ size 1336413848
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
results/AmazonCounterfactualClassification.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "1f7e6a9d6fa6e64c53d146e428565640410c0df1",
3
+ "task_name": "AmazonCounterfactualClassification",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "scores_per_experiment": [
9
+ {
10
+ "accuracy": 0.649254,
11
+ "f1": 0.586506,
12
+ "f1_weighted": 0.684595,
13
+ "precision": 0.600352,
14
+ "precision_weighted": 0.775368,
15
+ "recall": 0.654881,
16
+ "recall_weighted": 0.649254,
17
+ "ap": 0.273508,
18
+ "ap_weighted": 0.273508
19
+ },
20
+ {
21
+ "accuracy": 0.697015,
22
+ "f1": 0.641825,
23
+ "f1_weighted": 0.727443,
24
+ "precision": 0.647981,
25
+ "precision_weighted": 0.817523,
26
+ "recall": 0.727903,
27
+ "recall_weighted": 0.697015,
28
+ "ap": 0.331037,
29
+ "ap_weighted": 0.331037
30
+ },
31
+ {
32
+ "accuracy": 0.676119,
33
+ "f1": 0.624217,
34
+ "f1_weighted": 0.709262,
35
+ "precision": 0.637704,
36
+ "precision_weighted": 0.811853,
37
+ "recall": 0.714916,
38
+ "recall_weighted": 0.676119,
39
+ "ap": 0.317145,
40
+ "ap_weighted": 0.317145
41
+ },
42
+ {
43
+ "accuracy": 0.677612,
44
+ "f1": 0.621485,
45
+ "f1_weighted": 0.710244,
46
+ "precision": 0.631961,
47
+ "precision_weighted": 0.804421,
48
+ "recall": 0.704287,
49
+ "recall_weighted": 0.677612,
50
+ "ap": 0.310154,
51
+ "ap_weighted": 0.310154
52
+ },
53
+ {
54
+ "accuracy": 0.691045,
55
+ "f1": 0.634768,
56
+ "f1_weighted": 0.722072,
57
+ "precision": 0.641819,
58
+ "precision_weighted": 0.812023,
59
+ "recall": 0.718414,
60
+ "recall_weighted": 0.691045,
61
+ "ap": 0.322848,
62
+ "ap_weighted": 0.322848
63
+ },
64
+ {
65
+ "accuracy": 0.69403,
66
+ "f1": 0.628723,
67
+ "f1_weighted": 0.723546,
68
+ "precision": 0.630964,
69
+ "precision_weighted": 0.798047,
70
+ "recall": 0.697156,
71
+ "recall_weighted": 0.69403,
72
+ "ap": 0.308638,
73
+ "ap_weighted": 0.308638
74
+ },
75
+ {
76
+ "accuracy": 0.731343,
77
+ "f1": 0.667277,
78
+ "f1_weighted": 0.756185,
79
+ "precision": 0.661176,
80
+ "precision_weighted": 0.820221,
81
+ "recall": 0.737682,
82
+ "recall_weighted": 0.731343,
83
+ "ap": 0.34849,
84
+ "ap_weighted": 0.34849
85
+ },
86
+ {
87
+ "accuracy": 0.758209,
88
+ "f1": 0.690155,
89
+ "f1_weighted": 0.778582,
90
+ "precision": 0.677353,
91
+ "precision_weighted": 0.827304,
92
+ "recall": 0.751491,
93
+ "recall_weighted": 0.758209,
94
+ "ap": 0.369966,
95
+ "ap_weighted": 0.369966
96
+ },
97
+ {
98
+ "accuracy": 0.719403,
99
+ "f1": 0.667831,
100
+ "f1_weighted": 0.747533,
101
+ "precision": 0.670334,
102
+ "precision_weighted": 0.837169,
103
+ "recall": 0.762042,
104
+ "recall_weighted": 0.719403,
105
+ "ap": 0.362635,
106
+ "ap_weighted": 0.362635
107
+ },
108
+ {
109
+ "accuracy": 0.646269,
110
+ "f1": 0.590632,
111
+ "f1_weighted": 0.682534,
112
+ "precision": 0.608982,
113
+ "precision_weighted": 0.785877,
114
+ "recall": 0.670361,
115
+ "recall_weighted": 0.646269,
116
+ "ap": 0.282822,
117
+ "ap_weighted": 0.282822
118
+ }
119
+ ],
120
+ "accuracy": 0.69403,
121
+ "f1": 0.635342,
122
+ "f1_weighted": 0.7242,
123
+ "precision": 0.640863,
124
+ "precision_weighted": 0.808981,
125
+ "recall": 0.713913,
126
+ "recall_weighted": 0.69403,
127
+ "ap": 0.322724,
128
+ "ap_weighted": 0.322724,
129
+ "main_score": 0.69403,
130
+ "hf_subset": "en",
131
+ "languages": [
132
+ "eng-Latn"
133
+ ]
134
+ }
135
+ ]
136
+ },
137
+ "evaluation_time": 9.506344318389893,
138
+ "kg_co2_emissions": null
139
+ }
results/ArXivHierarchicalClusteringP2P.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "0bbdb47bcbe3a90093699aefeed338a0f28a7ee8",
3
+ "task_name": "ArXivHierarchicalClusteringP2P",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "v_measures": {
9
+ "Level 0": [
10
+ 0.588118,
11
+ 0.55789,
12
+ 0.588657,
13
+ 0.565098,
14
+ 0.531625,
15
+ 0.546981,
16
+ 0.553416,
17
+ 0.563032,
18
+ 0.582855,
19
+ 0.604549
20
+ ],
21
+ "Level 1": [
22
+ 0.55282,
23
+ 0.598374,
24
+ 0.553477,
25
+ 0.572985,
26
+ 0.578826,
27
+ 0.575859,
28
+ 0.567694,
29
+ 0.583048,
30
+ 0.570849,
31
+ 0.612438
32
+ ]
33
+ },
34
+ "v_measure": 0.57243,
35
+ "v_measure_std": 0.019856,
36
+ "main_score": 0.57243,
37
+ "hf_subset": "default",
38
+ "languages": [
39
+ "eng-Latn"
40
+ ]
41
+ }
42
+ ]
43
+ },
44
+ "evaluation_time": 3.604710817337036,
45
+ "kg_co2_emissions": null
46
+ }
results/ArXivHierarchicalClusteringS2S.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "b73bd54100e5abfa6e3a23dcafb46fe4d2438dc3",
3
+ "task_name": "ArXivHierarchicalClusteringS2S",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "v_measures": {
9
+ "Level 0": [
10
+ 0.552113,
11
+ 0.557846,
12
+ 0.615447,
13
+ 0.57622,
14
+ 0.60526,
15
+ 0.578992,
16
+ 0.518152,
17
+ 0.574417,
18
+ 0.585929,
19
+ 0.576289
20
+ ],
21
+ "Level 1": [
22
+ 0.56749,
23
+ 0.570838,
24
+ 0.572715,
25
+ 0.588897,
26
+ 0.593059,
27
+ 0.551369,
28
+ 0.578812,
29
+ 0.569051,
30
+ 0.555796,
31
+ 0.581776
32
+ ]
33
+ },
34
+ "v_measure": 0.573523,
35
+ "v_measure_std": 0.020394,
36
+ "main_score": 0.573523,
37
+ "hf_subset": "default",
38
+ "languages": [
39
+ "eng-Latn"
40
+ ]
41
+ }
42
+ ]
43
+ },
44
+ "evaluation_time": 2.6457130908966064,
45
+ "kg_co2_emissions": null
46
+ }
results/ArguAna.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "c22ab2a51041ffd869aaddef7af8d8215647e41a",
3
+ "task_name": "ArguAna",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "ndcg_at_1": 0.32148,
9
+ "ndcg_at_3": 0.47085,
10
+ "ndcg_at_5": 0.52582,
11
+ "ndcg_at_10": 0.56947,
12
+ "ndcg_at_20": 0.59348,
13
+ "ndcg_at_100": 0.60287,
14
+ "ndcg_at_1000": 0.60355,
15
+ "map_at_1": 0.32148,
16
+ "map_at_3": 0.43314,
17
+ "map_at_5": 0.46358,
18
+ "map_at_10": 0.48158,
19
+ "map_at_20": 0.48832,
20
+ "map_at_100": 0.48977,
21
+ "map_at_1000": 0.4898,
22
+ "recall_at_1": 0.32148,
23
+ "recall_at_3": 0.58037,
24
+ "recall_at_5": 0.71408,
25
+ "recall_at_10": 0.84922,
26
+ "recall_at_20": 0.9431,
27
+ "recall_at_100": 0.99147,
28
+ "recall_at_1000": 0.99644,
29
+ "accuracy": 0.32148,
30
+ "precision_at_1": 0.32148,
31
+ "precision_at_3": 0.19346,
32
+ "precision_at_5": 0.14282,
33
+ "precision_at_10": 0.08492,
34
+ "precision_at_20": 0.04716,
35
+ "precision_at_100": 0.00991,
36
+ "precision_at_1000": 0.001,
37
+ "mrr_at_1": 0.329303,
38
+ "mrr_at_3": 0.43504,
39
+ "mrr_at_5": 0.466086,
40
+ "mrr_at_10": 0.484421,
41
+ "mrr_at_20": 0.49116,
42
+ "mrr_at_100": 0.492611,
43
+ "mrr_at_1000": 0.492644,
44
+ "nauc_ndcg_at_1_max": -0.137668,
45
+ "nauc_ndcg_at_1_std": -0.154927,
46
+ "nauc_ndcg_at_1_diff1": 0.163325,
47
+ "nauc_ndcg_at_3_max": -0.115032,
48
+ "nauc_ndcg_at_3_std": -0.145246,
49
+ "nauc_ndcg_at_3_diff1": 0.108408,
50
+ "nauc_ndcg_at_5_max": -0.112043,
51
+ "nauc_ndcg_at_5_std": -0.143539,
52
+ "nauc_ndcg_at_5_diff1": 0.107012,
53
+ "nauc_ndcg_at_10_max": -0.097924,
54
+ "nauc_ndcg_at_10_std": -0.14503,
55
+ "nauc_ndcg_at_10_diff1": 0.118255,
56
+ "nauc_ndcg_at_20_max": -0.1007,
57
+ "nauc_ndcg_at_20_std": -0.140301,
58
+ "nauc_ndcg_at_20_diff1": 0.122813,
59
+ "nauc_ndcg_at_100_max": -0.107669,
60
+ "nauc_ndcg_at_100_std": -0.140242,
61
+ "nauc_ndcg_at_100_diff1": 0.124003,
62
+ "nauc_ndcg_at_1000_max": -0.10908,
63
+ "nauc_ndcg_at_1000_std": -0.141305,
64
+ "nauc_ndcg_at_1000_diff1": 0.123777,
65
+ "nauc_map_at_1_max": -0.137668,
66
+ "nauc_map_at_1_std": -0.154927,
67
+ "nauc_map_at_1_diff1": 0.163325,
68
+ "nauc_map_at_3_max": -0.120305,
69
+ "nauc_map_at_3_std": -0.147814,
70
+ "nauc_map_at_3_diff1": 0.120978,
71
+ "nauc_map_at_5_max": -0.119326,
72
+ "nauc_map_at_5_std": -0.147306,
73
+ "nauc_map_at_5_diff1": 0.120669,
74
+ "nauc_map_at_10_max": -0.114149,
75
+ "nauc_map_at_10_std": -0.147728,
76
+ "nauc_map_at_10_diff1": 0.125427,
77
+ "nauc_map_at_20_max": -0.115054,
78
+ "nauc_map_at_20_std": -0.146868,
79
+ "nauc_map_at_20_diff1": 0.126602,
80
+ "nauc_map_at_100_max": -0.115744,
81
+ "nauc_map_at_100_std": -0.146499,
82
+ "nauc_map_at_100_diff1": 0.126887,
83
+ "nauc_map_at_1000_max": -0.115782,
84
+ "nauc_map_at_1000_std": -0.146526,
85
+ "nauc_map_at_1000_diff1": 0.126888,
86
+ "nauc_recall_at_1_max": -0.137668,
87
+ "nauc_recall_at_1_std": -0.154927,
88
+ "nauc_recall_at_1_diff1": 0.163325,
89
+ "nauc_recall_at_3_max": -0.099047,
90
+ "nauc_recall_at_3_std": -0.137318,
91
+ "nauc_recall_at_3_diff1": 0.070409,
92
+ "nauc_recall_at_5_max": -0.083732,
93
+ "nauc_recall_at_5_std": -0.128521,
94
+ "nauc_recall_at_5_diff1": 0.056309,
95
+ "nauc_recall_at_10_max": 0.015354,
96
+ "nauc_recall_at_10_std": -0.12949,
97
+ "nauc_recall_at_10_diff1": 0.084682,
98
+ "nauc_recall_at_20_max": 0.139097,
99
+ "nauc_recall_at_20_std": -0.017415,
100
+ "nauc_recall_at_20_diff1": 0.112789,
101
+ "nauc_recall_at_100_max": 0.367691,
102
+ "nauc_recall_at_100_std": 0.492571,
103
+ "nauc_recall_at_100_diff1": 0.173819,
104
+ "nauc_recall_at_1000_max": 0.273904,
105
+ "nauc_recall_at_1000_std": 0.799704,
106
+ "nauc_recall_at_1000_diff1": 0.098469,
107
+ "nauc_precision_at_1_max": -0.137668,
108
+ "nauc_precision_at_1_std": -0.154927,
109
+ "nauc_precision_at_1_diff1": 0.163325,
110
+ "nauc_precision_at_3_max": -0.099047,
111
+ "nauc_precision_at_3_std": -0.137318,
112
+ "nauc_precision_at_3_diff1": 0.070409,
113
+ "nauc_precision_at_5_max": -0.083732,
114
+ "nauc_precision_at_5_std": -0.128521,
115
+ "nauc_precision_at_5_diff1": 0.056309,
116
+ "nauc_precision_at_10_max": 0.015354,
117
+ "nauc_precision_at_10_std": -0.12949,
118
+ "nauc_precision_at_10_diff1": 0.084682,
119
+ "nauc_precision_at_20_max": 0.139097,
120
+ "nauc_precision_at_20_std": -0.017415,
121
+ "nauc_precision_at_20_diff1": 0.112789,
122
+ "nauc_precision_at_100_max": 0.367691,
123
+ "nauc_precision_at_100_std": 0.492571,
124
+ "nauc_precision_at_100_diff1": 0.173819,
125
+ "nauc_precision_at_1000_max": 0.273904,
126
+ "nauc_precision_at_1000_std": 0.799704,
127
+ "nauc_precision_at_1000_diff1": 0.098469,
128
+ "nauc_mrr_at_1_max": -0.140931,
129
+ "nauc_mrr_at_1_std": -0.149755,
130
+ "nauc_mrr_at_1_diff1": 0.140384,
131
+ "nauc_mrr_at_3_max": -0.134722,
132
+ "nauc_mrr_at_3_std": -0.148001,
133
+ "nauc_mrr_at_3_diff1": 0.094973,
134
+ "nauc_mrr_at_5_max": -0.132923,
135
+ "nauc_mrr_at_5_std": -0.146442,
136
+ "nauc_mrr_at_5_diff1": 0.094969,
137
+ "nauc_mrr_at_10_max": -0.125777,
138
+ "nauc_mrr_at_10_std": -0.145776,
139
+ "nauc_mrr_at_10_diff1": 0.101029,
140
+ "nauc_mrr_at_20_max": -0.127278,
141
+ "nauc_mrr_at_20_std": -0.145178,
142
+ "nauc_mrr_at_20_diff1": 0.10156,
143
+ "nauc_mrr_at_100_max": -0.12775,
144
+ "nauc_mrr_at_100_std": -0.144507,
145
+ "nauc_mrr_at_100_diff1": 0.101768,
146
+ "nauc_mrr_at_1000_max": -0.127789,
147
+ "nauc_mrr_at_1000_std": -0.144533,
148
+ "nauc_mrr_at_1000_diff1": 0.101766,
149
+ "cv_recall_at_1": 0.3293,
150
+ "cv_recall_at_3": 0.57681,
151
+ "cv_recall_at_5": 0.71195,
152
+ "cv_recall_at_10": 0.84922,
153
+ "cv_recall_at_20": 0.9431,
154
+ "cv_recall_at_100": 0.99147,
155
+ "cv_recall_at_1000": 0.99644,
156
+ "main_score": 0.56947,
157
+ "hf_subset": "default",
158
+ "languages": [
159
+ "eng-Latn"
160
+ ]
161
+ }
162
+ ]
163
+ },
164
+ "evaluation_time": 84.46596837043762,
165
+ "kg_co2_emissions": null
166
+ }
results/AskUbuntuDupQuestions.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "c5691e3c48741d5f83b5cc8e630653d7a8cfc048",
3
+ "task_name": "AskUbuntuDupQuestions",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "ndcg_at_1": 0.63989,
9
+ "ndcg_at_3": 0.61439,
10
+ "ndcg_at_5": 0.62149,
11
+ "ndcg_at_10": 0.67771,
12
+ "ndcg_at_20": 0.77394,
13
+ "ndcg_at_100": 0.77394,
14
+ "ndcg_at_1000": 0.77394,
15
+ "map_at_1": 0.17446,
16
+ "map_at_3": 0.32949,
17
+ "map_at_5": 0.41096,
18
+ "map_at_10": 0.52723,
19
+ "map_at_20": 0.62452,
20
+ "map_at_100": 0.62452,
21
+ "map_at_1000": 0.62452,
22
+ "recall_at_1": 0.17446,
23
+ "recall_at_3": 0.38225,
24
+ "recall_at_5": 0.51771,
25
+ "recall_at_10": 0.74832,
26
+ "recall_at_20": 1.0,
27
+ "recall_at_100": 1.0,
28
+ "recall_at_1000": 1.0,
29
+ "accuracy": 0.17446,
30
+ "precision_at_1": 0.63989,
31
+ "precision_at_3": 0.54017,
32
+ "precision_at_5": 0.4759,
33
+ "precision_at_10": 0.38033,
34
+ "precision_at_20": 0.27355,
35
+ "precision_at_100": 0.05471,
36
+ "precision_at_1000": 0.00547,
37
+ "mrr_at_1": 0.639889,
38
+ "mrr_at_3": 0.736842,
39
+ "mrr_at_5": 0.748476,
40
+ "mrr_at_10": 0.756357,
41
+ "mrr_at_20": 0.75929,
42
+ "mrr_at_100": 0.75929,
43
+ "mrr_at_1000": 0.75929,
44
+ "nauc_ndcg_at_1_max": 0.265791,
45
+ "nauc_ndcg_at_1_std": 0.172433,
46
+ "nauc_ndcg_at_1_diff1": 0.1581,
47
+ "nauc_ndcg_at_3_max": 0.229131,
48
+ "nauc_ndcg_at_3_std": 0.163351,
49
+ "nauc_ndcg_at_3_diff1": 0.076223,
50
+ "nauc_ndcg_at_5_max": 0.148425,
51
+ "nauc_ndcg_at_5_std": 0.2084,
52
+ "nauc_ndcg_at_5_diff1": 0.073401,
53
+ "nauc_ndcg_at_10_max": 0.150451,
54
+ "nauc_ndcg_at_10_std": 0.278433,
55
+ "nauc_ndcg_at_10_diff1": 0.058024,
56
+ "nauc_ndcg_at_20_max": 0.220443,
57
+ "nauc_ndcg_at_20_std": 0.182049,
58
+ "nauc_ndcg_at_20_diff1": 0.104532,
59
+ "nauc_ndcg_at_100_max": 0.220443,
60
+ "nauc_ndcg_at_100_std": 0.182049,
61
+ "nauc_ndcg_at_100_diff1": 0.104532,
62
+ "nauc_ndcg_at_1000_max": 0.220443,
63
+ "nauc_ndcg_at_1000_std": 0.182049,
64
+ "nauc_ndcg_at_1000_diff1": 0.104532,
65
+ "nauc_map_at_1_max": 0.001463,
66
+ "nauc_map_at_1_std": 0.058585,
67
+ "nauc_map_at_1_diff1": 0.322998,
68
+ "nauc_map_at_3_max": 0.034507,
69
+ "nauc_map_at_3_std": 0.154627,
70
+ "nauc_map_at_3_diff1": 0.218079,
71
+ "nauc_map_at_5_max": 0.036509,
72
+ "nauc_map_at_5_std": 0.211766,
73
+ "nauc_map_at_5_diff1": 0.164591,
74
+ "nauc_map_at_10_max": 0.116807,
75
+ "nauc_map_at_10_std": 0.261467,
76
+ "nauc_map_at_10_diff1": 0.100653,
77
+ "nauc_map_at_20_max": 0.175436,
78
+ "nauc_map_at_20_std": 0.20505,
79
+ "nauc_map_at_20_diff1": 0.092236,
80
+ "nauc_map_at_100_max": 0.175436,
81
+ "nauc_map_at_100_std": 0.20505,
82
+ "nauc_map_at_100_diff1": 0.092236,
83
+ "nauc_map_at_1000_max": 0.175436,
84
+ "nauc_map_at_1000_std": 0.20505,
85
+ "nauc_map_at_1000_diff1": 0.092236,
86
+ "nauc_recall_at_1_max": 0.001463,
87
+ "nauc_recall_at_1_std": 0.058585,
88
+ "nauc_recall_at_1_diff1": 0.322998,
89
+ "nauc_recall_at_3_max": -0.017355,
90
+ "nauc_recall_at_3_std": 0.137604,
91
+ "nauc_recall_at_3_diff1": 0.184745,
92
+ "nauc_recall_at_5_max": -0.085968,
93
+ "nauc_recall_at_5_std": 0.217856,
94
+ "nauc_recall_at_5_diff1": 0.093926,
95
+ "nauc_recall_at_10_max": -0.061708,
96
+ "nauc_recall_at_10_std": 0.344954,
97
+ "nauc_recall_at_10_diff1": -0.038761,
98
+ "nauc_recall_at_20_max": NaN,
99
+ "nauc_recall_at_20_std": NaN,
100
+ "nauc_recall_at_20_diff1": NaN,
101
+ "nauc_recall_at_100_max": NaN,
102
+ "nauc_recall_at_100_std": NaN,
103
+ "nauc_recall_at_100_diff1": NaN,
104
+ "nauc_recall_at_1000_max": NaN,
105
+ "nauc_recall_at_1000_std": NaN,
106
+ "nauc_recall_at_1000_diff1": NaN,
107
+ "nauc_precision_at_1_max": 0.265791,
108
+ "nauc_precision_at_1_std": 0.172433,
109
+ "nauc_precision_at_1_diff1": 0.1581,
110
+ "nauc_precision_at_3_max": 0.249078,
111
+ "nauc_precision_at_3_std": 0.16048,
112
+ "nauc_precision_at_3_diff1": -0.078452,
113
+ "nauc_precision_at_5_max": 0.199954,
114
+ "nauc_precision_at_5_std": 0.156313,
115
+ "nauc_precision_at_5_diff1": -0.13117,
116
+ "nauc_precision_at_10_max": 0.214771,
117
+ "nauc_precision_at_10_std": 0.088996,
118
+ "nauc_precision_at_10_diff1": -0.165939,
119
+ "nauc_precision_at_20_max": 0.182085,
120
+ "nauc_precision_at_20_std": -0.033402,
121
+ "nauc_precision_at_20_diff1": -0.119829,
122
+ "nauc_precision_at_100_max": 0.182085,
123
+ "nauc_precision_at_100_std": -0.033402,
124
+ "nauc_precision_at_100_diff1": -0.119829,
125
+ "nauc_precision_at_1000_max": 0.182085,
126
+ "nauc_precision_at_1000_std": -0.033402,
127
+ "nauc_precision_at_1000_diff1": -0.119829,
128
+ "nauc_mrr_at_1_max": 0.265791,
129
+ "nauc_mrr_at_1_std": 0.172433,
130
+ "nauc_mrr_at_1_diff1": 0.1581,
131
+ "nauc_mrr_at_3_max": 0.284328,
132
+ "nauc_mrr_at_3_std": 0.16625,
133
+ "nauc_mrr_at_3_diff1": 0.153301,
134
+ "nauc_mrr_at_5_max": 0.27045,
135
+ "nauc_mrr_at_5_std": 0.170954,
136
+ "nauc_mrr_at_5_diff1": 0.143117,
137
+ "nauc_mrr_at_10_max": 0.273181,
138
+ "nauc_mrr_at_10_std": 0.169639,
139
+ "nauc_mrr_at_10_diff1": 0.147531,
140
+ "nauc_mrr_at_20_max": 0.27723,
141
+ "nauc_mrr_at_20_std": 0.167568,
142
+ "nauc_mrr_at_20_diff1": 0.148917,
143
+ "nauc_mrr_at_100_max": 0.27723,
144
+ "nauc_mrr_at_100_std": 0.167568,
145
+ "nauc_mrr_at_100_diff1": 0.148917,
146
+ "nauc_mrr_at_1000_max": 0.27723,
147
+ "nauc_mrr_at_1000_std": 0.167568,
148
+ "nauc_mrr_at_1000_diff1": 0.148917,
149
+ "cv_recall_at_1": 0.63989,
150
+ "cv_recall_at_3": 0.85596,
151
+ "cv_recall_at_5": 0.90582,
152
+ "cv_recall_at_10": 0.96399,
153
+ "cv_recall_at_20": 1.0,
154
+ "cv_recall_at_100": 1.0,
155
+ "cv_recall_at_1000": 1.0,
156
+ "main_score": 0.62452,
157
+ "hf_subset": "default",
158
+ "languages": [
159
+ "eng-Latn"
160
+ ]
161
+ }
162
+ ]
163
+ },
164
+ "evaluation_time": 6.776808500289917,
165
+ "kg_co2_emissions": null
166
+ }
results/BIOSSES.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "d3fb88f8f02e40887cd149695127462bbcf29b4a",
3
+ "task_name": "BIOSSES",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "pearson": 0.911029,
9
+ "spearman": 0.883683,
10
+ "cosine_pearson": 0.911029,
11
+ "cosine_spearman": 0.883683,
12
+ "manhattan_pearson": 0.896267,
13
+ "manhattan_spearman": 0.880761,
14
+ "euclidean_pearson": 0.897434,
15
+ "euclidean_spearman": 0.883683,
16
+ "main_score": 0.883683,
17
+ "hf_subset": "default",
18
+ "languages": [
19
+ "eng-Latn"
20
+ ]
21
+ }
22
+ ]
23
+ },
24
+ "evaluation_time": 0.4675290584564209,
25
+ "kg_co2_emissions": null
26
+ }
results/Banking77Classification.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "0fd18e25b25c072e09e0d92ab615fda904d66300",
3
+ "task_name": "Banking77Classification",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "scores_per_experiment": [
9
+ {
10
+ "accuracy": 0.807468,
11
+ "f1": 0.798371,
12
+ "f1_weighted": 0.798371,
13
+ "precision": 0.819092,
14
+ "precision_weighted": 0.819092,
15
+ "recall": 0.807468,
16
+ "recall_weighted": 0.807468,
17
+ "ap": null,
18
+ "ap_weighted": null
19
+ },
20
+ {
21
+ "accuracy": 0.809416,
22
+ "f1": 0.802365,
23
+ "f1_weighted": 0.802365,
24
+ "precision": 0.821554,
25
+ "precision_weighted": 0.821554,
26
+ "recall": 0.809416,
27
+ "recall_weighted": 0.809416,
28
+ "ap": null,
29
+ "ap_weighted": null
30
+ },
31
+ {
32
+ "accuracy": 0.808117,
33
+ "f1": 0.801029,
34
+ "f1_weighted": 0.801029,
35
+ "precision": 0.826254,
36
+ "precision_weighted": 0.826254,
37
+ "recall": 0.808117,
38
+ "recall_weighted": 0.808117,
39
+ "ap": null,
40
+ "ap_weighted": null
41
+ },
42
+ {
43
+ "accuracy": 0.809091,
44
+ "f1": 0.804207,
45
+ "f1_weighted": 0.804207,
46
+ "precision": 0.820275,
47
+ "precision_weighted": 0.820275,
48
+ "recall": 0.809091,
49
+ "recall_weighted": 0.809091,
50
+ "ap": null,
51
+ "ap_weighted": null
52
+ },
53
+ {
54
+ "accuracy": 0.798377,
55
+ "f1": 0.788723,
56
+ "f1_weighted": 0.788723,
57
+ "precision": 0.815261,
58
+ "precision_weighted": 0.815261,
59
+ "recall": 0.798377,
60
+ "recall_weighted": 0.798377,
61
+ "ap": null,
62
+ "ap_weighted": null
63
+ },
64
+ {
65
+ "accuracy": 0.799675,
66
+ "f1": 0.795388,
67
+ "f1_weighted": 0.795388,
68
+ "precision": 0.814753,
69
+ "precision_weighted": 0.814753,
70
+ "recall": 0.799675,
71
+ "recall_weighted": 0.799675,
72
+ "ap": null,
73
+ "ap_weighted": null
74
+ },
75
+ {
76
+ "accuracy": 0.785065,
77
+ "f1": 0.775255,
78
+ "f1_weighted": 0.775255,
79
+ "precision": 0.802057,
80
+ "precision_weighted": 0.802057,
81
+ "recall": 0.785065,
82
+ "recall_weighted": 0.785065,
83
+ "ap": null,
84
+ "ap_weighted": null
85
+ },
86
+ {
87
+ "accuracy": 0.787662,
88
+ "f1": 0.777538,
89
+ "f1_weighted": 0.777538,
90
+ "precision": 0.804055,
91
+ "precision_weighted": 0.804055,
92
+ "recall": 0.787662,
93
+ "recall_weighted": 0.787662,
94
+ "ap": null,
95
+ "ap_weighted": null
96
+ },
97
+ {
98
+ "accuracy": 0.810065,
99
+ "f1": 0.801736,
100
+ "f1_weighted": 0.801736,
101
+ "precision": 0.82562,
102
+ "precision_weighted": 0.82562,
103
+ "recall": 0.810065,
104
+ "recall_weighted": 0.810065,
105
+ "ap": null,
106
+ "ap_weighted": null
107
+ },
108
+ {
109
+ "accuracy": 0.799675,
110
+ "f1": 0.791429,
111
+ "f1_weighted": 0.791429,
112
+ "precision": 0.815973,
113
+ "precision_weighted": 0.815973,
114
+ "recall": 0.799675,
115
+ "recall_weighted": 0.799675,
116
+ "ap": null,
117
+ "ap_weighted": null
118
+ }
119
+ ],
120
+ "accuracy": 0.801461,
121
+ "f1": 0.793604,
122
+ "f1_weighted": 0.793604,
123
+ "precision": 0.816489,
124
+ "precision_weighted": 0.816489,
125
+ "recall": 0.801461,
126
+ "recall_weighted": 0.801461,
127
+ "ap": NaN,
128
+ "ap_weighted": NaN,
129
+ "main_score": 0.801461,
130
+ "hf_subset": "default",
131
+ "languages": [
132
+ "eng-Latn"
133
+ ]
134
+ }
135
+ ]
136
+ },
137
+ "evaluation_time": 29.597341775894165,
138
+ "kg_co2_emissions": null
139
+ }
results/BiorxivClusteringP2P.v2.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "f5dbc242e11dd8e24def4c4268607a49e02946dc",
3
+ "task_name": "BiorxivClusteringP2P.v2",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "v_measures": {
9
+ "Level 0": [
10
+ 0.387412,
11
+ 0.384082,
12
+ 0.390527,
13
+ 0.385893,
14
+ 0.38434,
15
+ 0.376143,
16
+ 0.384562,
17
+ 0.369675,
18
+ 0.382281,
19
+ 0.38791
20
+ ]
21
+ },
22
+ "v_measure": 0.383282,
23
+ "v_measure_std": 0.005816,
24
+ "main_score": 0.383282,
25
+ "hf_subset": "default",
26
+ "languages": [
27
+ "eng-Latn"
28
+ ]
29
+ }
30
+ ]
31
+ },
32
+ "evaluation_time": 32.374085664749146,
33
+ "kg_co2_emissions": null
34
+ }
results/CQADupstackGamingRetrieval.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "4885aa143210c98657558c04aaf3dc47cfb54340",
3
+ "task_name": "CQADupstackGamingRetrieval",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "ndcg_at_1": 0.51599,
9
+ "ndcg_at_3": 0.58421,
10
+ "ndcg_at_5": 0.60729,
11
+ "ndcg_at_10": 0.63083,
12
+ "ndcg_at_20": 0.64652,
13
+ "ndcg_at_100": 0.66617,
14
+ "ndcg_at_1000": 0.67593,
15
+ "map_at_1": 0.45155,
16
+ "map_at_3": 0.54827,
17
+ "map_at_5": 0.56535,
18
+ "map_at_10": 0.57784,
19
+ "map_at_20": 0.58353,
20
+ "map_at_100": 0.5872,
21
+ "map_at_1000": 0.58768,
22
+ "recall_at_1": 0.45155,
23
+ "recall_at_3": 0.62863,
24
+ "recall_at_5": 0.68581,
25
+ "recall_at_10": 0.75316,
26
+ "recall_at_20": 0.81107,
27
+ "recall_at_100": 0.90434,
28
+ "recall_at_1000": 0.97398,
29
+ "accuracy": 0.45155,
30
+ "precision_at_1": 0.51599,
31
+ "precision_at_3": 0.25873,
32
+ "precision_at_5": 0.17429,
33
+ "precision_at_10": 0.09881,
34
+ "precision_at_20": 0.05445,
35
+ "precision_at_100": 0.01251,
36
+ "precision_at_1000": 0.00137,
37
+ "mrr_at_1": 0.515987,
38
+ "mrr_at_3": 0.589655,
39
+ "mrr_at_5": 0.601661,
40
+ "mrr_at_10": 0.61012,
41
+ "mrr_at_20": 0.613576,
42
+ "mrr_at_100": 0.61577,
43
+ "mrr_at_1000": 0.616017,
44
+ "nauc_ndcg_at_1_max": 0.506098,
45
+ "nauc_ndcg_at_1_std": 0.041661,
46
+ "nauc_ndcg_at_1_diff1": 0.628427,
47
+ "nauc_ndcg_at_3_max": 0.493851,
48
+ "nauc_ndcg_at_3_std": 0.036568,
49
+ "nauc_ndcg_at_3_diff1": 0.587003,
50
+ "nauc_ndcg_at_5_max": 0.497129,
51
+ "nauc_ndcg_at_5_std": 0.048214,
52
+ "nauc_ndcg_at_5_diff1": 0.579579,
53
+ "nauc_ndcg_at_10_max": 0.510384,
54
+ "nauc_ndcg_at_10_std": 0.075512,
55
+ "nauc_ndcg_at_10_diff1": 0.57767,
56
+ "nauc_ndcg_at_20_max": 0.514116,
57
+ "nauc_ndcg_at_20_std": 0.079624,
58
+ "nauc_ndcg_at_20_diff1": 0.577835,
59
+ "nauc_ndcg_at_100_max": 0.519925,
60
+ "nauc_ndcg_at_100_std": 0.089295,
61
+ "nauc_ndcg_at_100_diff1": 0.579443,
62
+ "nauc_ndcg_at_1000_max": 0.518541,
63
+ "nauc_ndcg_at_1000_std": 0.083625,
64
+ "nauc_ndcg_at_1000_diff1": 0.582874,
65
+ "nauc_map_at_1_max": 0.431799,
66
+ "nauc_map_at_1_std": 0.002154,
67
+ "nauc_map_at_1_diff1": 0.631826,
68
+ "nauc_map_at_3_max": 0.479552,
69
+ "nauc_map_at_3_std": 0.018832,
70
+ "nauc_map_at_3_diff1": 0.600169,
71
+ "nauc_map_at_5_max": 0.485417,
72
+ "nauc_map_at_5_std": 0.030139,
73
+ "nauc_map_at_5_diff1": 0.593826,
74
+ "nauc_map_at_10_max": 0.493785,
75
+ "nauc_map_at_10_std": 0.045101,
76
+ "nauc_map_at_10_diff1": 0.592386,
77
+ "nauc_map_at_20_max": 0.497375,
78
+ "nauc_map_at_20_std": 0.050127,
79
+ "nauc_map_at_20_diff1": 0.591999,
80
+ "nauc_map_at_100_max": 0.499353,
81
+ "nauc_map_at_100_std": 0.053156,
82
+ "nauc_map_at_100_diff1": 0.591782,
83
+ "nauc_map_at_1000_max": 0.499487,
84
+ "nauc_map_at_1000_std": 0.053079,
85
+ "nauc_map_at_1000_diff1": 0.591855,
86
+ "nauc_recall_at_1_max": 0.431799,
87
+ "nauc_recall_at_1_std": 0.002154,
88
+ "nauc_recall_at_1_diff1": 0.631826,
89
+ "nauc_recall_at_3_max": 0.463324,
90
+ "nauc_recall_at_3_std": 0.012701,
91
+ "nauc_recall_at_3_diff1": 0.551161,
92
+ "nauc_recall_at_5_max": 0.465674,
93
+ "nauc_recall_at_5_std": 0.042598,
94
+ "nauc_recall_at_5_diff1": 0.525423,
95
+ "nauc_recall_at_10_max": 0.509617,
96
+ "nauc_recall_at_10_std": 0.145078,
97
+ "nauc_recall_at_10_diff1": 0.505253,
98
+ "nauc_recall_at_20_max": 0.534538,
99
+ "nauc_recall_at_20_std": 0.181317,
100
+ "nauc_recall_at_20_diff1": 0.486676,
101
+ "nauc_recall_at_100_max": 0.606471,
102
+ "nauc_recall_at_100_std": 0.350025,
103
+ "nauc_recall_at_100_diff1": 0.454987,
104
+ "nauc_recall_at_1000_max": 0.74056,
105
+ "nauc_recall_at_1000_std": 0.610781,
106
+ "nauc_recall_at_1000_diff1": 0.465264,
107
+ "nauc_precision_at_1_max": 0.506098,
108
+ "nauc_precision_at_1_std": 0.041661,
109
+ "nauc_precision_at_1_diff1": 0.628427,
110
+ "nauc_precision_at_3_max": 0.429175,
111
+ "nauc_precision_at_3_std": 0.099613,
112
+ "nauc_precision_at_3_diff1": 0.308909,
113
+ "nauc_precision_at_5_max": 0.382707,
114
+ "nauc_precision_at_5_std": 0.145784,
115
+ "nauc_precision_at_5_diff1": 0.200923,
116
+ "nauc_precision_at_10_max": 0.345298,
117
+ "nauc_precision_at_10_std": 0.230198,
118
+ "nauc_precision_at_10_diff1": 0.091341,
119
+ "nauc_precision_at_20_max": 0.302119,
120
+ "nauc_precision_at_20_std": 0.266458,
121
+ "nauc_precision_at_20_diff1": 0.005037,
122
+ "nauc_precision_at_100_max": 0.229357,
123
+ "nauc_precision_at_100_std": 0.301516,
124
+ "nauc_precision_at_100_diff1": -0.117012,
125
+ "nauc_precision_at_1000_max": 0.166249,
126
+ "nauc_precision_at_1000_std": 0.252757,
127
+ "nauc_precision_at_1000_diff1": -0.175149,
128
+ "nauc_mrr_at_1_max": 0.506098,
129
+ "nauc_mrr_at_1_std": 0.041661,
130
+ "nauc_mrr_at_1_diff1": 0.628427,
131
+ "nauc_mrr_at_3_max": 0.51335,
132
+ "nauc_mrr_at_3_std": 0.056645,
133
+ "nauc_mrr_at_3_diff1": 0.594636,
134
+ "nauc_mrr_at_5_max": 0.512302,
135
+ "nauc_mrr_at_5_std": 0.060036,
136
+ "nauc_mrr_at_5_diff1": 0.59263,
137
+ "nauc_mrr_at_10_max": 0.516189,
138
+ "nauc_mrr_at_10_std": 0.069241,
139
+ "nauc_mrr_at_10_diff1": 0.59238,
140
+ "nauc_mrr_at_20_max": 0.515782,
141
+ "nauc_mrr_at_20_std": 0.06798,
142
+ "nauc_mrr_at_20_diff1": 0.592112,
143
+ "nauc_mrr_at_100_max": 0.515903,
144
+ "nauc_mrr_at_100_std": 0.067966,
145
+ "nauc_mrr_at_100_diff1": 0.592683,
146
+ "nauc_mrr_at_1000_max": 0.515814,
147
+ "nauc_mrr_at_1000_std": 0.067834,
148
+ "nauc_mrr_at_1000_diff1": 0.592781,
149
+ "cv_recall_at_1": 0.51599,
150
+ "cv_recall_at_3": 0.6815,
151
+ "cv_recall_at_5": 0.73417,
152
+ "cv_recall_at_10": 0.79624,
153
+ "cv_recall_at_20": 0.84702,
154
+ "cv_recall_at_100": 0.92476,
155
+ "cv_recall_at_1000": 0.97868,
156
+ "main_score": 0.63083,
157
+ "hf_subset": "default",
158
+ "languages": [
159
+ "eng-Latn"
160
+ ]
161
+ }
162
+ ]
163
+ },
164
+ "evaluation_time": 220.85158777236938,
165
+ "kg_co2_emissions": null
166
+ }
results/CQADupstackUnixRetrieval.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "6c6430d3a6d36f8d2a829195bc5dc94d7e063e53",
3
+ "task_name": "CQADupstackUnixRetrieval",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "ndcg_at_1": 0.35354,
9
+ "ndcg_at_3": 0.39745,
10
+ "ndcg_at_5": 0.4196,
11
+ "ndcg_at_10": 0.44524,
12
+ "ndcg_at_20": 0.46497,
13
+ "ndcg_at_100": 0.49622,
14
+ "ndcg_at_1000": 0.51772,
15
+ "map_at_1": 0.30026,
16
+ "map_at_3": 0.36435,
17
+ "map_at_5": 0.38008,
18
+ "map_at_10": 0.39323,
19
+ "map_at_20": 0.39982,
20
+ "map_at_100": 0.40478,
21
+ "map_at_1000": 0.40575,
22
+ "recall_at_1": 0.30026,
23
+ "recall_at_3": 0.42884,
24
+ "recall_at_5": 0.48623,
25
+ "recall_at_10": 0.55973,
26
+ "recall_at_20": 0.63044,
27
+ "recall_at_100": 0.78034,
28
+ "recall_at_1000": 0.92923,
29
+ "accuracy": 0.30026,
30
+ "precision_at_1": 0.35354,
31
+ "precision_at_3": 0.17942,
32
+ "precision_at_5": 0.12519,
33
+ "precision_at_10": 0.07472,
34
+ "precision_at_20": 0.04286,
35
+ "precision_at_100": 0.01113,
36
+ "precision_at_1000": 0.00142,
37
+ "mrr_at_1": 0.353545,
38
+ "mrr_at_3": 0.411847,
39
+ "mrr_at_5": 0.425653,
40
+ "mrr_at_10": 0.434839,
41
+ "mrr_at_20": 0.439338,
42
+ "mrr_at_100": 0.4432,
43
+ "mrr_at_1000": 0.44369,
44
+ "nauc_ndcg_at_1_max": 0.409556,
45
+ "nauc_ndcg_at_1_std": 0.009214,
46
+ "nauc_ndcg_at_1_diff1": 0.600343,
47
+ "nauc_ndcg_at_3_max": 0.404932,
48
+ "nauc_ndcg_at_3_std": 0.034435,
49
+ "nauc_ndcg_at_3_diff1": 0.552751,
50
+ "nauc_ndcg_at_5_max": 0.406843,
51
+ "nauc_ndcg_at_5_std": 0.044595,
52
+ "nauc_ndcg_at_5_diff1": 0.548815,
53
+ "nauc_ndcg_at_10_max": 0.411187,
54
+ "nauc_ndcg_at_10_std": 0.065134,
55
+ "nauc_ndcg_at_10_diff1": 0.531634,
56
+ "nauc_ndcg_at_20_max": 0.417229,
57
+ "nauc_ndcg_at_20_std": 0.073945,
58
+ "nauc_ndcg_at_20_diff1": 0.524353,
59
+ "nauc_ndcg_at_100_max": 0.42016,
60
+ "nauc_ndcg_at_100_std": 0.085366,
61
+ "nauc_ndcg_at_100_diff1": 0.522318,
62
+ "nauc_ndcg_at_1000_max": 0.41966,
63
+ "nauc_ndcg_at_1000_std": 0.078716,
64
+ "nauc_ndcg_at_1000_diff1": 0.53003,
65
+ "nauc_map_at_1_max": 0.397619,
66
+ "nauc_map_at_1_std": 0.00705,
67
+ "nauc_map_at_1_diff1": 0.628473,
68
+ "nauc_map_at_3_max": 0.403544,
69
+ "nauc_map_at_3_std": 0.024338,
70
+ "nauc_map_at_3_diff1": 0.581648,
71
+ "nauc_map_at_5_max": 0.406442,
72
+ "nauc_map_at_5_std": 0.031071,
73
+ "nauc_map_at_5_diff1": 0.575364,
74
+ "nauc_map_at_10_max": 0.408445,
75
+ "nauc_map_at_10_std": 0.04121,
76
+ "nauc_map_at_10_diff1": 0.565085,
77
+ "nauc_map_at_20_max": 0.409285,
78
+ "nauc_map_at_20_std": 0.043553,
79
+ "nauc_map_at_20_diff1": 0.561293,
80
+ "nauc_map_at_100_max": 0.41014,
81
+ "nauc_map_at_100_std": 0.04552,
82
+ "nauc_map_at_100_diff1": 0.560791,
83
+ "nauc_map_at_1000_max": 0.410268,
84
+ "nauc_map_at_1000_std": 0.045483,
85
+ "nauc_map_at_1000_diff1": 0.561177,
86
+ "nauc_recall_at_1_max": 0.397619,
87
+ "nauc_recall_at_1_std": 0.00705,
88
+ "nauc_recall_at_1_diff1": 0.628473,
89
+ "nauc_recall_at_3_max": 0.391441,
90
+ "nauc_recall_at_3_std": 0.046483,
91
+ "nauc_recall_at_3_diff1": 0.518344,
92
+ "nauc_recall_at_5_max": 0.391173,
93
+ "nauc_recall_at_5_std": 0.071157,
94
+ "nauc_recall_at_5_diff1": 0.491936,
95
+ "nauc_recall_at_10_max": 0.400903,
96
+ "nauc_recall_at_10_std": 0.126967,
97
+ "nauc_recall_at_10_diff1": 0.436789,
98
+ "nauc_recall_at_20_max": 0.426741,
99
+ "nauc_recall_at_20_std": 0.170802,
100
+ "nauc_recall_at_20_diff1": 0.403286,
101
+ "nauc_recall_at_100_max": 0.450633,
102
+ "nauc_recall_at_100_std": 0.296233,
103
+ "nauc_recall_at_100_diff1": 0.342181,
104
+ "nauc_recall_at_1000_max": 0.523321,
105
+ "nauc_recall_at_1000_std": 0.460469,
106
+ "nauc_recall_at_1000_diff1": 0.324336,
107
+ "nauc_precision_at_1_max": 0.409556,
108
+ "nauc_precision_at_1_std": 0.009214,
109
+ "nauc_precision_at_1_diff1": 0.600343,
110
+ "nauc_precision_at_3_max": 0.365536,
111
+ "nauc_precision_at_3_std": 0.065121,
112
+ "nauc_precision_at_3_diff1": 0.387956,
113
+ "nauc_precision_at_5_max": 0.341395,
114
+ "nauc_precision_at_5_std": 0.08963,
115
+ "nauc_precision_at_5_diff1": 0.309794,
116
+ "nauc_precision_at_10_max": 0.291684,
117
+ "nauc_precision_at_10_std": 0.135798,
118
+ "nauc_precision_at_10_diff1": 0.177327,
119
+ "nauc_precision_at_20_max": 0.261713,
120
+ "nauc_precision_at_20_std": 0.141277,
121
+ "nauc_precision_at_20_diff1": 0.092982,
122
+ "nauc_precision_at_100_max": 0.160884,
123
+ "nauc_precision_at_100_std": 0.166291,
124
+ "nauc_precision_at_100_diff1": -0.069392,
125
+ "nauc_precision_at_1000_max": -0.000994,
126
+ "nauc_precision_at_1000_std": 0.069137,
127
+ "nauc_precision_at_1000_diff1": -0.200592,
128
+ "nauc_mrr_at_1_max": 0.409556,
129
+ "nauc_mrr_at_1_std": 0.009214,
130
+ "nauc_mrr_at_1_diff1": 0.600343,
131
+ "nauc_mrr_at_3_max": 0.408135,
132
+ "nauc_mrr_at_3_std": 0.034196,
133
+ "nauc_mrr_at_3_diff1": 0.551259,
134
+ "nauc_mrr_at_5_max": 0.407147,
135
+ "nauc_mrr_at_5_std": 0.039286,
136
+ "nauc_mrr_at_5_diff1": 0.546022,
137
+ "nauc_mrr_at_10_max": 0.407566,
138
+ "nauc_mrr_at_10_std": 0.045942,
139
+ "nauc_mrr_at_10_diff1": 0.540061,
140
+ "nauc_mrr_at_20_max": 0.409829,
141
+ "nauc_mrr_at_20_std": 0.047779,
142
+ "nauc_mrr_at_20_diff1": 0.540346,
143
+ "nauc_mrr_at_100_max": 0.409639,
144
+ "nauc_mrr_at_100_std": 0.048153,
145
+ "nauc_mrr_at_100_diff1": 0.541034,
146
+ "nauc_mrr_at_1000_max": 0.409636,
147
+ "nauc_mrr_at_1000_std": 0.048022,
148
+ "nauc_mrr_at_1000_diff1": 0.541307,
149
+ "cv_recall_at_1": 0.35354,
150
+ "cv_recall_at_3": 0.48601,
151
+ "cv_recall_at_5": 0.54664,
152
+ "cv_recall_at_10": 0.61474,
153
+ "cv_recall_at_20": 0.6791,
154
+ "cv_recall_at_100": 0.82743,
155
+ "cv_recall_at_1000": 0.94683,
156
+ "main_score": 0.44524,
157
+ "hf_subset": "default",
158
+ "languages": [
159
+ "eng-Latn"
160
+ ]
161
+ }
162
+ ]
163
+ },
164
+ "evaluation_time": 434.9975244998932,
165
+ "kg_co2_emissions": null
166
+ }
results/ClimateFEVERHardNegatives.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "3a309e201f3c2c4b13bd4a367a8f37eee2ec1d21",
3
+ "task_name": "ClimateFEVERHardNegatives",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "ndcg_at_1": 0.274,
9
+ "ndcg_at_3": 0.25284,
10
+ "ndcg_at_5": 0.2787,
11
+ "ndcg_at_10": 0.31641,
12
+ "ndcg_at_20": 0.34692,
13
+ "ndcg_at_100": 0.39902,
14
+ "ndcg_at_1000": 0.43489,
15
+ "map_at_1": 0.12962,
16
+ "map_at_3": 0.18739,
17
+ "map_at_5": 0.20859,
18
+ "map_at_10": 0.22755,
19
+ "map_at_20": 0.23877,
20
+ "map_at_100": 0.24944,
21
+ "map_at_1000": 0.25161,
22
+ "recall_at_1": 0.12962,
23
+ "recall_at_3": 0.23967,
24
+ "recall_at_5": 0.30417,
25
+ "recall_at_10": 0.38742,
26
+ "recall_at_20": 0.47315,
27
+ "recall_at_100": 0.66883,
28
+ "recall_at_1000": 0.86628,
29
+ "accuracy": 0.12962,
30
+ "precision_at_1": 0.274,
31
+ "precision_at_3": 0.18867,
32
+ "precision_at_5": 0.1494,
33
+ "precision_at_10": 0.1,
34
+ "precision_at_20": 0.06325,
35
+ "precision_at_100": 0.01903,
36
+ "precision_at_1000": 0.00258,
37
+ "mrr_at_1": 0.274,
38
+ "mrr_at_3": 0.367333,
39
+ "mrr_at_5": 0.389983,
40
+ "mrr_at_10": 0.403317,
41
+ "mrr_at_20": 0.40885,
42
+ "mrr_at_100": 0.412573,
43
+ "mrr_at_1000": 0.412909,
44
+ "nauc_ndcg_at_1_max": 0.275002,
45
+ "nauc_ndcg_at_1_std": 0.122164,
46
+ "nauc_ndcg_at_1_diff1": 0.220439,
47
+ "nauc_ndcg_at_3_max": 0.284449,
48
+ "nauc_ndcg_at_3_std": 0.129309,
49
+ "nauc_ndcg_at_3_diff1": 0.186314,
50
+ "nauc_ndcg_at_5_max": 0.300668,
51
+ "nauc_ndcg_at_5_std": 0.155444,
52
+ "nauc_ndcg_at_5_diff1": 0.190257,
53
+ "nauc_ndcg_at_10_max": 0.325913,
54
+ "nauc_ndcg_at_10_std": 0.171467,
55
+ "nauc_ndcg_at_10_diff1": 0.181151,
56
+ "nauc_ndcg_at_20_max": 0.346924,
57
+ "nauc_ndcg_at_20_std": 0.200727,
58
+ "nauc_ndcg_at_20_diff1": 0.18155,
59
+ "nauc_ndcg_at_100_max": 0.357512,
60
+ "nauc_ndcg_at_100_std": 0.208152,
61
+ "nauc_ndcg_at_100_diff1": 0.187862,
62
+ "nauc_ndcg_at_1000_max": 0.360926,
63
+ "nauc_ndcg_at_1000_std": 0.212201,
64
+ "nauc_ndcg_at_1000_diff1": 0.189039,
65
+ "nauc_map_at_1_max": 0.2736,
66
+ "nauc_map_at_1_std": 0.093326,
67
+ "nauc_map_at_1_diff1": 0.240344,
68
+ "nauc_map_at_3_max": 0.286962,
69
+ "nauc_map_at_3_std": 0.113945,
70
+ "nauc_map_at_3_diff1": 0.204302,
71
+ "nauc_map_at_5_max": 0.291701,
72
+ "nauc_map_at_5_std": 0.133445,
73
+ "nauc_map_at_5_diff1": 0.201218,
74
+ "nauc_map_at_10_max": 0.306761,
75
+ "nauc_map_at_10_std": 0.142935,
76
+ "nauc_map_at_10_diff1": 0.193629,
77
+ "nauc_map_at_20_max": 0.317513,
78
+ "nauc_map_at_20_std": 0.157381,
79
+ "nauc_map_at_20_diff1": 0.193446,
80
+ "nauc_map_at_100_max": 0.322498,
81
+ "nauc_map_at_100_std": 0.161539,
82
+ "nauc_map_at_100_diff1": 0.194639,
83
+ "nauc_map_at_1000_max": 0.322859,
84
+ "nauc_map_at_1000_std": 0.162051,
85
+ "nauc_map_at_1000_diff1": 0.19471,
86
+ "nauc_recall_at_1_max": 0.2736,
87
+ "nauc_recall_at_1_std": 0.093326,
88
+ "nauc_recall_at_1_diff1": 0.240344,
89
+ "nauc_recall_at_3_max": 0.260145,
90
+ "nauc_recall_at_3_std": 0.110288,
91
+ "nauc_recall_at_3_diff1": 0.160259,
92
+ "nauc_recall_at_5_max": 0.270657,
93
+ "nauc_recall_at_5_std": 0.15409,
94
+ "nauc_recall_at_5_diff1": 0.15819,
95
+ "nauc_recall_at_10_max": 0.307294,
96
+ "nauc_recall_at_10_std": 0.179697,
97
+ "nauc_recall_at_10_diff1": 0.133445,
98
+ "nauc_recall_at_20_max": 0.345342,
99
+ "nauc_recall_at_20_std": 0.242711,
100
+ "nauc_recall_at_20_diff1": 0.128101,
101
+ "nauc_recall_at_100_max": 0.373719,
102
+ "nauc_recall_at_100_std": 0.266078,
103
+ "nauc_recall_at_100_diff1": 0.141145,
104
+ "nauc_recall_at_1000_max": 0.488096,
105
+ "nauc_recall_at_1000_std": 0.389173,
106
+ "nauc_recall_at_1000_diff1": 0.152554,
107
+ "nauc_precision_at_1_max": 0.275002,
108
+ "nauc_precision_at_1_std": 0.122164,
109
+ "nauc_precision_at_1_diff1": 0.220439,
110
+ "nauc_precision_at_3_max": 0.276123,
111
+ "nauc_precision_at_3_std": 0.152041,
112
+ "nauc_precision_at_3_diff1": 0.131149,
113
+ "nauc_precision_at_5_max": 0.279261,
114
+ "nauc_precision_at_5_std": 0.201392,
115
+ "nauc_precision_at_5_diff1": 0.114826,
116
+ "nauc_precision_at_10_max": 0.296186,
117
+ "nauc_precision_at_10_std": 0.202752,
118
+ "nauc_precision_at_10_diff1": 0.078298,
119
+ "nauc_precision_at_20_max": 0.304496,
120
+ "nauc_precision_at_20_std": 0.251276,
121
+ "nauc_precision_at_20_diff1": 0.057876,
122
+ "nauc_precision_at_100_max": 0.2377,
123
+ "nauc_precision_at_100_std": 0.221926,
124
+ "nauc_precision_at_100_diff1": 0.037494,
125
+ "nauc_precision_at_1000_max": 0.104284,
126
+ "nauc_precision_at_1000_std": 0.156004,
127
+ "nauc_precision_at_1000_diff1": -0.038072,
128
+ "nauc_mrr_at_1_max": 0.275002,
129
+ "nauc_mrr_at_1_std": 0.122164,
130
+ "nauc_mrr_at_1_diff1": 0.220439,
131
+ "nauc_mrr_at_3_max": 0.291465,
132
+ "nauc_mrr_at_3_std": 0.148645,
133
+ "nauc_mrr_at_3_diff1": 0.182407,
134
+ "nauc_mrr_at_5_max": 0.306729,
135
+ "nauc_mrr_at_5_std": 0.165051,
136
+ "nauc_mrr_at_5_diff1": 0.191357,
137
+ "nauc_mrr_at_10_max": 0.311964,
138
+ "nauc_mrr_at_10_std": 0.16869,
139
+ "nauc_mrr_at_10_diff1": 0.190986,
140
+ "nauc_mrr_at_20_max": 0.314436,
141
+ "nauc_mrr_at_20_std": 0.171688,
142
+ "nauc_mrr_at_20_diff1": 0.192286,
143
+ "nauc_mrr_at_100_max": 0.312318,
144
+ "nauc_mrr_at_100_std": 0.169257,
145
+ "nauc_mrr_at_100_diff1": 0.192123,
146
+ "nauc_mrr_at_1000_max": 0.312261,
147
+ "nauc_mrr_at_1000_std": 0.169235,
148
+ "nauc_mrr_at_1000_diff1": 0.192166,
149
+ "cv_recall_at_1": 0.274,
150
+ "cv_recall_at_3": 0.492,
151
+ "cv_recall_at_5": 0.59,
152
+ "cv_recall_at_10": 0.688,
153
+ "cv_recall_at_20": 0.767,
154
+ "cv_recall_at_100": 0.899,
155
+ "cv_recall_at_1000": 0.971,
156
+ "main_score": 0.31641,
157
+ "hf_subset": "default",
158
+ "languages": [
159
+ "eng-Latn"
160
+ ]
161
+ }
162
+ ]
163
+ },
164
+ "evaluation_time": 449.19873213768005,
165
+ "kg_co2_emissions": null
166
+ }
results/FEVERHardNegatives.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "080c9ed6267b65029207906e815d44a9240bafca",
3
+ "task_name": "FEVERHardNegatives",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "ndcg_at_1": 0.723,
9
+ "ndcg_at_3": 0.80965,
10
+ "ndcg_at_5": 0.82436,
11
+ "ndcg_at_10": 0.83392,
12
+ "ndcg_at_20": 0.83828,
13
+ "ndcg_at_100": 0.84387,
14
+ "ndcg_at_1000": 0.84603,
15
+ "map_at_1": 0.68043,
16
+ "map_at_3": 0.7728,
17
+ "map_at_5": 0.78226,
18
+ "map_at_10": 0.78688,
19
+ "map_at_20": 0.78877,
20
+ "map_at_100": 0.78989,
21
+ "map_at_1000": 0.79002,
22
+ "recall_at_1": 0.68043,
23
+ "recall_at_3": 0.87424,
24
+ "recall_at_5": 0.91081,
25
+ "recall_at_10": 0.93953,
26
+ "recall_at_20": 0.9537,
27
+ "recall_at_100": 0.97873,
28
+ "recall_at_1000": 0.9915,
29
+ "accuracy": 0.68043,
30
+ "precision_at_1": 0.723,
31
+ "precision_at_3": 0.312,
32
+ "precision_at_5": 0.1962,
33
+ "precision_at_10": 0.102,
34
+ "precision_at_20": 0.05245,
35
+ "precision_at_100": 0.01097,
36
+ "precision_at_1000": 0.00114,
37
+ "mrr_at_1": 0.723,
38
+ "mrr_at_3": 0.813667,
39
+ "mrr_at_5": 0.821917,
40
+ "mrr_at_10": 0.82505,
41
+ "mrr_at_20": 0.825488,
42
+ "mrr_at_100": 0.825904,
43
+ "mrr_at_1000": 0.825907,
44
+ "nauc_ndcg_at_1_max": 0.191433,
45
+ "nauc_ndcg_at_1_std": -0.003952,
46
+ "nauc_ndcg_at_1_diff1": 0.645189,
47
+ "nauc_ndcg_at_3_max": 0.210584,
48
+ "nauc_ndcg_at_3_std": 0.001842,
49
+ "nauc_ndcg_at_3_diff1": 0.569072,
50
+ "nauc_ndcg_at_5_max": 0.221259,
51
+ "nauc_ndcg_at_5_std": 0.004782,
52
+ "nauc_ndcg_at_5_diff1": 0.580388,
53
+ "nauc_ndcg_at_10_max": 0.22841,
54
+ "nauc_ndcg_at_10_std": 0.017083,
55
+ "nauc_ndcg_at_10_diff1": 0.58087,
56
+ "nauc_ndcg_at_20_max": 0.229352,
57
+ "nauc_ndcg_at_20_std": 0.015047,
58
+ "nauc_ndcg_at_20_diff1": 0.588067,
59
+ "nauc_ndcg_at_100_max": 0.220972,
60
+ "nauc_ndcg_at_100_std": 0.015389,
61
+ "nauc_ndcg_at_100_diff1": 0.587182,
62
+ "nauc_ndcg_at_1000_max": 0.222632,
63
+ "nauc_ndcg_at_1000_std": 0.017141,
64
+ "nauc_ndcg_at_1000_diff1": 0.592045,
65
+ "nauc_map_at_1_max": 0.16553,
66
+ "nauc_map_at_1_std": -0.023371,
67
+ "nauc_map_at_1_diff1": 0.602886,
68
+ "nauc_map_at_3_max": 0.193374,
69
+ "nauc_map_at_3_std": -0.005847,
70
+ "nauc_map_at_3_diff1": 0.572508,
71
+ "nauc_map_at_5_max": 0.19982,
72
+ "nauc_map_at_5_std": -0.004019,
73
+ "nauc_map_at_5_diff1": 0.579187,
74
+ "nauc_map_at_10_max": 0.203747,
75
+ "nauc_map_at_10_std": 0.000742,
76
+ "nauc_map_at_10_diff1": 0.579909,
77
+ "nauc_map_at_20_max": 0.203833,
78
+ "nauc_map_at_20_std": -0.000136,
79
+ "nauc_map_at_20_diff1": 0.582332,
80
+ "nauc_map_at_100_max": 0.20356,
81
+ "nauc_map_at_100_std": 0.000742,
82
+ "nauc_map_at_100_diff1": 0.582569,
83
+ "nauc_map_at_1000_max": 0.203793,
84
+ "nauc_map_at_1000_std": 0.000968,
85
+ "nauc_map_at_1000_diff1": 0.582794,
86
+ "nauc_recall_at_1_max": 0.16553,
87
+ "nauc_recall_at_1_std": -0.023371,
88
+ "nauc_recall_at_1_diff1": 0.602886,
89
+ "nauc_recall_at_3_max": 0.233446,
90
+ "nauc_recall_at_3_std": 0.011379,
91
+ "nauc_recall_at_3_diff1": 0.454025,
92
+ "nauc_recall_at_5_max": 0.292924,
93
+ "nauc_recall_at_5_std": 0.036591,
94
+ "nauc_recall_at_5_diff1": 0.460081,
95
+ "nauc_recall_at_10_max": 0.352647,
96
+ "nauc_recall_at_10_std": 0.130195,
97
+ "nauc_recall_at_10_diff1": 0.396073,
98
+ "nauc_recall_at_20_max": 0.411616,
99
+ "nauc_recall_at_20_std": 0.145556,
100
+ "nauc_recall_at_20_diff1": 0.44071,
101
+ "nauc_recall_at_100_max": 0.329347,
102
+ "nauc_recall_at_100_std": 0.241695,
103
+ "nauc_recall_at_100_diff1": 0.297613,
104
+ "nauc_recall_at_1000_max": 0.640089,
105
+ "nauc_recall_at_1000_std": 0.683766,
106
+ "nauc_recall_at_1000_diff1": 0.451477,
107
+ "nauc_precision_at_1_max": 0.191433,
108
+ "nauc_precision_at_1_std": -0.003952,
109
+ "nauc_precision_at_1_diff1": 0.645189,
110
+ "nauc_precision_at_3_max": 0.24903,
111
+ "nauc_precision_at_3_std": 0.041802,
112
+ "nauc_precision_at_3_diff1": 0.358315,
113
+ "nauc_precision_at_5_max": 0.241888,
114
+ "nauc_precision_at_5_std": 0.061622,
115
+ "nauc_precision_at_5_diff1": 0.206315,
116
+ "nauc_precision_at_10_max": 0.22659,
117
+ "nauc_precision_at_10_std": 0.133015,
118
+ "nauc_precision_at_10_diff1": 0.000137,
119
+ "nauc_precision_at_20_max": 0.15251,
120
+ "nauc_precision_at_20_std": 0.101556,
121
+ "nauc_precision_at_20_diff1": -0.057582,
122
+ "nauc_precision_at_100_max": 0.050364,
123
+ "nauc_precision_at_100_std": 0.107559,
124
+ "nauc_precision_at_100_diff1": -0.176048,
125
+ "nauc_precision_at_1000_max": 0.013929,
126
+ "nauc_precision_at_1000_std": 0.092803,
127
+ "nauc_precision_at_1000_diff1": -0.180184,
128
+ "nauc_mrr_at_1_max": 0.191433,
129
+ "nauc_mrr_at_1_std": -0.003952,
130
+ "nauc_mrr_at_1_diff1": 0.645189,
131
+ "nauc_mrr_at_3_max": 0.222359,
132
+ "nauc_mrr_at_3_std": 0.011258,
133
+ "nauc_mrr_at_3_diff1": 0.62291,
134
+ "nauc_mrr_at_5_max": 0.226662,
135
+ "nauc_mrr_at_5_std": 0.009859,
136
+ "nauc_mrr_at_5_diff1": 0.633058,
137
+ "nauc_mrr_at_10_max": 0.225692,
138
+ "nauc_mrr_at_10_std": 0.014149,
139
+ "nauc_mrr_at_10_diff1": 0.631578,
140
+ "nauc_mrr_at_20_max": 0.225323,
141
+ "nauc_mrr_at_20_std": 0.014336,
142
+ "nauc_mrr_at_20_diff1": 0.631543,
143
+ "nauc_mrr_at_100_max": 0.223509,
144
+ "nauc_mrr_at_100_std": 0.013261,
145
+ "nauc_mrr_at_100_diff1": 0.631251,
146
+ "nauc_mrr_at_1000_max": 0.223515,
147
+ "nauc_mrr_at_1000_std": 0.013259,
148
+ "nauc_mrr_at_1000_diff1": 0.631288,
149
+ "cv_recall_at_1": 0.723,
150
+ "cv_recall_at_3": 0.92,
151
+ "cv_recall_at_5": 0.955,
152
+ "cv_recall_at_10": 0.979,
153
+ "cv_recall_at_20": 0.985,
154
+ "cv_recall_at_100": 0.999,
155
+ "cv_recall_at_1000": 1.0,
156
+ "main_score": 0.83392,
157
+ "hf_subset": "default",
158
+ "languages": [
159
+ "eng-Latn"
160
+ ]
161
+ }
162
+ ]
163
+ },
164
+ "evaluation_time": 976.1986212730408,
165
+ "kg_co2_emissions": null
166
+ }
results/FiQA2018.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "27a168819829fe9bcd655c2df245fb19452e8e06",
3
+ "task_name": "FiQA2018",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "ndcg_at_1": 0.375,
9
+ "ndcg_at_3": 0.34229,
10
+ "ndcg_at_5": 0.35733,
11
+ "ndcg_at_10": 0.38399,
12
+ "ndcg_at_20": 0.41091,
13
+ "ndcg_at_100": 0.45563,
14
+ "ndcg_at_1000": 0.48646,
15
+ "map_at_1": 0.18198,
16
+ "map_at_3": 0.26456,
17
+ "map_at_5": 0.28813,
18
+ "map_at_10": 0.30688,
19
+ "map_at_20": 0.31708,
20
+ "map_at_100": 0.32581,
21
+ "map_at_1000": 0.32763,
22
+ "recall_at_1": 0.18198,
23
+ "recall_at_3": 0.30919,
24
+ "recall_at_5": 0.37729,
25
+ "recall_at_10": 0.45993,
26
+ "recall_at_20": 0.54379,
27
+ "recall_at_100": 0.72737,
28
+ "recall_at_1000": 0.91103,
29
+ "accuracy": 0.18198,
30
+ "precision_at_1": 0.375,
31
+ "precision_at_3": 0.22891,
32
+ "precision_at_5": 0.17099,
33
+ "precision_at_10": 0.10802,
34
+ "precision_at_20": 0.06489,
35
+ "precision_at_100": 0.0181,
36
+ "precision_at_1000": 0.00236,
37
+ "mrr_at_1": 0.375,
38
+ "mrr_at_3": 0.430041,
39
+ "mrr_at_5": 0.446245,
40
+ "mrr_at_10": 0.45733,
41
+ "mrr_at_20": 0.463166,
42
+ "mrr_at_100": 0.46702,
43
+ "mrr_at_1000": 0.46741,
44
+ "nauc_ndcg_at_1_max": 0.432019,
45
+ "nauc_ndcg_at_1_std": 0.011637,
46
+ "nauc_ndcg_at_1_diff1": 0.50781,
47
+ "nauc_ndcg_at_3_max": 0.377345,
48
+ "nauc_ndcg_at_3_std": 0.007846,
49
+ "nauc_ndcg_at_3_diff1": 0.396671,
50
+ "nauc_ndcg_at_5_max": 0.372312,
51
+ "nauc_ndcg_at_5_std": 0.022132,
52
+ "nauc_ndcg_at_5_diff1": 0.393079,
53
+ "nauc_ndcg_at_10_max": 0.368956,
54
+ "nauc_ndcg_at_10_std": 0.034727,
55
+ "nauc_ndcg_at_10_diff1": 0.392666,
56
+ "nauc_ndcg_at_20_max": 0.367152,
57
+ "nauc_ndcg_at_20_std": 0.040631,
58
+ "nauc_ndcg_at_20_diff1": 0.391096,
59
+ "nauc_ndcg_at_100_max": 0.383589,
60
+ "nauc_ndcg_at_100_std": 0.06035,
61
+ "nauc_ndcg_at_100_diff1": 0.395879,
62
+ "nauc_ndcg_at_1000_max": 0.394338,
63
+ "nauc_ndcg_at_1000_std": 0.058401,
64
+ "nauc_ndcg_at_1000_diff1": 0.399579,
65
+ "nauc_map_at_1_max": 0.280681,
66
+ "nauc_map_at_1_std": -0.043068,
67
+ "nauc_map_at_1_diff1": 0.472478,
68
+ "nauc_map_at_3_max": 0.306401,
69
+ "nauc_map_at_3_std": -0.019628,
70
+ "nauc_map_at_3_diff1": 0.395193,
71
+ "nauc_map_at_5_max": 0.325728,
72
+ "nauc_map_at_5_std": -0.002456,
73
+ "nauc_map_at_5_diff1": 0.387357,
74
+ "nauc_map_at_10_max": 0.339965,
75
+ "nauc_map_at_10_std": 0.008224,
76
+ "nauc_map_at_10_diff1": 0.385345,
77
+ "nauc_map_at_20_max": 0.344063,
78
+ "nauc_map_at_20_std": 0.012537,
79
+ "nauc_map_at_20_diff1": 0.385086,
80
+ "nauc_map_at_100_max": 0.349009,
81
+ "nauc_map_at_100_std": 0.017644,
82
+ "nauc_map_at_100_diff1": 0.386153,
83
+ "nauc_map_at_1000_max": 0.350017,
84
+ "nauc_map_at_1000_std": 0.018342,
85
+ "nauc_map_at_1000_diff1": 0.386509,
86
+ "nauc_recall_at_1_max": 0.280681,
87
+ "nauc_recall_at_1_std": -0.043068,
88
+ "nauc_recall_at_1_diff1": 0.472478,
89
+ "nauc_recall_at_3_max": 0.261153,
90
+ "nauc_recall_at_3_std": -0.019772,
91
+ "nauc_recall_at_3_diff1": 0.337431,
92
+ "nauc_recall_at_5_max": 0.27848,
93
+ "nauc_recall_at_5_std": 0.028899,
94
+ "nauc_recall_at_5_diff1": 0.301238,
95
+ "nauc_recall_at_10_max": 0.279161,
96
+ "nauc_recall_at_10_std": 0.070669,
97
+ "nauc_recall_at_10_diff1": 0.277259,
98
+ "nauc_recall_at_20_max": 0.258229,
99
+ "nauc_recall_at_20_std": 0.087949,
100
+ "nauc_recall_at_20_diff1": 0.257636,
101
+ "nauc_recall_at_100_max": 0.279181,
102
+ "nauc_recall_at_100_std": 0.191472,
103
+ "nauc_recall_at_100_diff1": 0.240476,
104
+ "nauc_recall_at_1000_max": 0.333851,
105
+ "nauc_recall_at_1000_std": 0.29943,
106
+ "nauc_recall_at_1000_diff1": 0.194119,
107
+ "nauc_precision_at_1_max": 0.432019,
108
+ "nauc_precision_at_1_std": 0.011637,
109
+ "nauc_precision_at_1_diff1": 0.50781,
110
+ "nauc_precision_at_3_max": 0.405411,
111
+ "nauc_precision_at_3_std": 0.058565,
112
+ "nauc_precision_at_3_diff1": 0.281176,
113
+ "nauc_precision_at_5_max": 0.426389,
114
+ "nauc_precision_at_5_std": 0.104337,
115
+ "nauc_precision_at_5_diff1": 0.234056,
116
+ "nauc_precision_at_10_max": 0.409292,
117
+ "nauc_precision_at_10_std": 0.124352,
118
+ "nauc_precision_at_10_diff1": 0.193568,
119
+ "nauc_precision_at_20_max": 0.386563,
120
+ "nauc_precision_at_20_std": 0.139659,
121
+ "nauc_precision_at_20_diff1": 0.168046,
122
+ "nauc_precision_at_100_max": 0.338433,
123
+ "nauc_precision_at_100_std": 0.165646,
124
+ "nauc_precision_at_100_diff1": 0.094026,
125
+ "nauc_precision_at_1000_max": 0.275791,
126
+ "nauc_precision_at_1000_std": 0.126994,
127
+ "nauc_precision_at_1000_diff1": 0.011416,
128
+ "nauc_mrr_at_1_max": 0.432019,
129
+ "nauc_mrr_at_1_std": 0.011637,
130
+ "nauc_mrr_at_1_diff1": 0.50781,
131
+ "nauc_mrr_at_3_max": 0.437244,
132
+ "nauc_mrr_at_3_std": 0.020764,
133
+ "nauc_mrr_at_3_diff1": 0.479167,
134
+ "nauc_mrr_at_5_max": 0.446956,
135
+ "nauc_mrr_at_5_std": 0.035922,
136
+ "nauc_mrr_at_5_diff1": 0.474751,
137
+ "nauc_mrr_at_10_max": 0.442342,
138
+ "nauc_mrr_at_10_std": 0.037219,
139
+ "nauc_mrr_at_10_diff1": 0.471361,
140
+ "nauc_mrr_at_20_max": 0.440519,
141
+ "nauc_mrr_at_20_std": 0.03651,
142
+ "nauc_mrr_at_20_diff1": 0.471232,
143
+ "nauc_mrr_at_100_max": 0.441316,
144
+ "nauc_mrr_at_100_std": 0.037822,
145
+ "nauc_mrr_at_100_diff1": 0.471791,
146
+ "nauc_mrr_at_1000_max": 0.441237,
147
+ "nauc_mrr_at_1000_std": 0.037637,
148
+ "nauc_mrr_at_1000_diff1": 0.471768,
149
+ "cv_recall_at_1": 0.375,
150
+ "cv_recall_at_3": 0.5,
151
+ "cv_recall_at_5": 0.57099,
152
+ "cv_recall_at_10": 0.65432,
153
+ "cv_recall_at_20": 0.73611,
154
+ "cv_recall_at_100": 0.88272,
155
+ "cv_recall_at_1000": 0.96914,
156
+ "main_score": 0.38399,
157
+ "hf_subset": "default",
158
+ "languages": [
159
+ "eng-Latn"
160
+ ]
161
+ }
162
+ ]
163
+ },
164
+ "evaluation_time": 444.3285460472107,
165
+ "kg_co2_emissions": null
166
+ }
results/HotpotQAHardNegatives.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "617612fa63afcb60e3b134bed8b7216a99707c37",
3
+ "task_name": "HotpotQAHardNegatives",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "ndcg_at_1": 0.729,
9
+ "ndcg_at_3": 0.62293,
10
+ "ndcg_at_5": 0.6556,
11
+ "ndcg_at_10": 0.68112,
12
+ "ndcg_at_20": 0.70156,
13
+ "ndcg_at_100": 0.72383,
14
+ "ndcg_at_1000": 0.73493,
15
+ "map_at_1": 0.3645,
16
+ "map_at_3": 0.5505,
17
+ "map_at_5": 0.57508,
18
+ "map_at_10": 0.59043,
19
+ "map_at_20": 0.59873,
20
+ "map_at_100": 0.60327,
21
+ "map_at_1000": 0.60392,
22
+ "recall_at_1": 0.3645,
23
+ "recall_at_3": 0.6055,
24
+ "recall_at_5": 0.67,
25
+ "recall_at_10": 0.734,
26
+ "recall_at_20": 0.8,
27
+ "recall_at_100": 0.899,
28
+ "recall_at_1000": 0.9705,
29
+ "accuracy": 0.3645,
30
+ "precision_at_1": 0.729,
31
+ "precision_at_3": 0.40367,
32
+ "precision_at_5": 0.268,
33
+ "precision_at_10": 0.1468,
34
+ "precision_at_20": 0.08,
35
+ "precision_at_100": 0.01798,
36
+ "precision_at_1000": 0.00194,
37
+ "mrr_at_1": 0.729,
38
+ "mrr_at_3": 0.795333,
39
+ "mrr_at_5": 0.805483,
40
+ "mrr_at_10": 0.809386,
41
+ "mrr_at_20": 0.811079,
42
+ "mrr_at_100": 0.811773,
43
+ "mrr_at_1000": 0.811804,
44
+ "nauc_ndcg_at_1_max": 0.369861,
45
+ "nauc_ndcg_at_1_std": -0.039125,
46
+ "nauc_ndcg_at_1_diff1": 0.680307,
47
+ "nauc_ndcg_at_3_max": 0.219673,
48
+ "nauc_ndcg_at_3_std": -0.070498,
49
+ "nauc_ndcg_at_3_diff1": 0.272915,
50
+ "nauc_ndcg_at_5_max": 0.216289,
51
+ "nauc_ndcg_at_5_std": -0.072227,
52
+ "nauc_ndcg_at_5_diff1": 0.26269,
53
+ "nauc_ndcg_at_10_max": 0.221594,
54
+ "nauc_ndcg_at_10_std": -0.058656,
55
+ "nauc_ndcg_at_10_diff1": 0.256044,
56
+ "nauc_ndcg_at_20_max": 0.23696,
57
+ "nauc_ndcg_at_20_std": -0.037726,
58
+ "nauc_ndcg_at_20_diff1": 0.27135,
59
+ "nauc_ndcg_at_100_max": 0.249425,
60
+ "nauc_ndcg_at_100_std": -0.013916,
61
+ "nauc_ndcg_at_100_diff1": 0.279371,
62
+ "nauc_ndcg_at_1000_max": 0.250371,
63
+ "nauc_ndcg_at_1000_std": -0.02157,
64
+ "nauc_ndcg_at_1000_diff1": 0.290888,
65
+ "nauc_map_at_1_max": 0.369861,
66
+ "nauc_map_at_1_std": -0.039125,
67
+ "nauc_map_at_1_diff1": 0.680307,
68
+ "nauc_map_at_3_max": 0.19206,
69
+ "nauc_map_at_3_std": -0.068545,
70
+ "nauc_map_at_3_diff1": 0.219745,
71
+ "nauc_map_at_5_max": 0.192975,
72
+ "nauc_map_at_5_std": -0.067257,
73
+ "nauc_map_at_5_diff1": 0.21607,
74
+ "nauc_map_at_10_max": 0.196566,
75
+ "nauc_map_at_10_std": -0.058636,
76
+ "nauc_map_at_10_diff1": 0.213755,
77
+ "nauc_map_at_20_max": 0.202241,
78
+ "nauc_map_at_20_std": -0.051256,
79
+ "nauc_map_at_20_diff1": 0.219067,
80
+ "nauc_map_at_100_max": 0.20403,
81
+ "nauc_map_at_100_std": -0.047927,
82
+ "nauc_map_at_100_diff1": 0.219233,
83
+ "nauc_map_at_1000_max": 0.203993,
84
+ "nauc_map_at_1000_std": -0.048104,
85
+ "nauc_map_at_1000_diff1": 0.21955,
86
+ "nauc_recall_at_1_max": 0.369861,
87
+ "nauc_recall_at_1_std": -0.039125,
88
+ "nauc_recall_at_1_diff1": 0.680307,
89
+ "nauc_recall_at_3_max": 0.164313,
90
+ "nauc_recall_at_3_std": -0.082302,
91
+ "nauc_recall_at_3_diff1": 0.132921,
92
+ "nauc_recall_at_5_max": 0.14463,
93
+ "nauc_recall_at_5_std": -0.085649,
94
+ "nauc_recall_at_5_diff1": 0.09513,
95
+ "nauc_recall_at_10_max": 0.144863,
96
+ "nauc_recall_at_10_std": -0.0479,
97
+ "nauc_recall_at_10_diff1": 0.051961,
98
+ "nauc_recall_at_20_max": 0.186944,
99
+ "nauc_recall_at_20_std": 0.033846,
100
+ "nauc_recall_at_20_diff1": 0.072496,
101
+ "nauc_recall_at_100_max": 0.264744,
102
+ "nauc_recall_at_100_std": 0.294387,
103
+ "nauc_recall_at_100_diff1": 0.017548,
104
+ "nauc_recall_at_1000_max": 0.41959,
105
+ "nauc_recall_at_1000_std": 0.61813,
106
+ "nauc_recall_at_1000_diff1": 0.000435,
107
+ "nauc_precision_at_1_max": 0.369861,
108
+ "nauc_precision_at_1_std": -0.039125,
109
+ "nauc_precision_at_1_diff1": 0.680307,
110
+ "nauc_precision_at_3_max": 0.164313,
111
+ "nauc_precision_at_3_std": -0.082302,
112
+ "nauc_precision_at_3_diff1": 0.132921,
113
+ "nauc_precision_at_5_max": 0.14463,
114
+ "nauc_precision_at_5_std": -0.085649,
115
+ "nauc_precision_at_5_diff1": 0.09513,
116
+ "nauc_precision_at_10_max": 0.144863,
117
+ "nauc_precision_at_10_std": -0.0479,
118
+ "nauc_precision_at_10_diff1": 0.051961,
119
+ "nauc_precision_at_20_max": 0.186944,
120
+ "nauc_precision_at_20_std": 0.033846,
121
+ "nauc_precision_at_20_diff1": 0.072496,
122
+ "nauc_precision_at_100_max": 0.264744,
123
+ "nauc_precision_at_100_std": 0.294387,
124
+ "nauc_precision_at_100_diff1": 0.017548,
125
+ "nauc_precision_at_1000_max": 0.41959,
126
+ "nauc_precision_at_1000_std": 0.61813,
127
+ "nauc_precision_at_1000_diff1": 0.000435,
128
+ "nauc_mrr_at_1_max": 0.369861,
129
+ "nauc_mrr_at_1_std": -0.039125,
130
+ "nauc_mrr_at_1_diff1": 0.680307,
131
+ "nauc_mrr_at_3_max": 0.384418,
132
+ "nauc_mrr_at_3_std": -0.052231,
133
+ "nauc_mrr_at_3_diff1": 0.657352,
134
+ "nauc_mrr_at_5_max": 0.382984,
135
+ "nauc_mrr_at_5_std": -0.057018,
136
+ "nauc_mrr_at_5_diff1": 0.659249,
137
+ "nauc_mrr_at_10_max": 0.382164,
138
+ "nauc_mrr_at_10_std": -0.059489,
139
+ "nauc_mrr_at_10_diff1": 0.658394,
140
+ "nauc_mrr_at_20_max": 0.383474,
141
+ "nauc_mrr_at_20_std": -0.057479,
142
+ "nauc_mrr_at_20_diff1": 0.659516,
143
+ "nauc_mrr_at_100_max": 0.382755,
144
+ "nauc_mrr_at_100_std": -0.056768,
145
+ "nauc_mrr_at_100_diff1": 0.659356,
146
+ "nauc_mrr_at_1000_max": 0.382769,
147
+ "nauc_mrr_at_1000_std": -0.056755,
148
+ "nauc_mrr_at_1000_diff1": 0.659379,
149
+ "cv_recall_at_1": 0.729,
150
+ "cv_recall_at_3": 0.874,
151
+ "cv_recall_at_5": 0.917,
152
+ "cv_recall_at_10": 0.946,
153
+ "cv_recall_at_20": 0.97,
154
+ "cv_recall_at_100": 0.995,
155
+ "cv_recall_at_1000": 1.0,
156
+ "main_score": 0.68112,
157
+ "hf_subset": "default",
158
+ "languages": [
159
+ "eng-Latn"
160
+ ]
161
+ }
162
+ ]
163
+ },
164
+ "evaluation_time": 836.6955578327179,
165
+ "kg_co2_emissions": null
166
+ }
results/ImdbClassification.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "3d86128a09e091d6018b6d26cad27f2739fc2db7",
3
+ "task_name": "ImdbClassification",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "scores_per_experiment": [
9
+ {
10
+ "accuracy": 0.76804,
11
+ "f1": 0.765902,
12
+ "f1_weighted": 0.765902,
13
+ "precision": 0.778202,
14
+ "precision_weighted": 0.778202,
15
+ "recall": 0.76804,
16
+ "recall_weighted": 0.76804,
17
+ "ap": 0.722841,
18
+ "ap_weighted": 0.722841
19
+ },
20
+ {
21
+ "accuracy": 0.76148,
22
+ "f1": 0.761348,
23
+ "f1_weighted": 0.761348,
24
+ "precision": 0.762058,
25
+ "precision_weighted": 0.762058,
26
+ "recall": 0.76148,
27
+ "recall_weighted": 0.76148,
28
+ "ap": 0.702481,
29
+ "ap_weighted": 0.702481
30
+ },
31
+ {
32
+ "accuracy": 0.69928,
33
+ "f1": 0.689458,
34
+ "f1_weighted": 0.689458,
35
+ "precision": 0.728142,
36
+ "precision_weighted": 0.728142,
37
+ "recall": 0.69928,
38
+ "recall_weighted": 0.69928,
39
+ "ap": 0.628933,
40
+ "ap_weighted": 0.628933
41
+ },
42
+ {
43
+ "accuracy": 0.78904,
44
+ "f1": 0.788367,
45
+ "f1_weighted": 0.788367,
46
+ "precision": 0.792765,
47
+ "precision_weighted": 0.792765,
48
+ "recall": 0.78904,
49
+ "recall_weighted": 0.78904,
50
+ "ap": 0.738686,
51
+ "ap_weighted": 0.738686
52
+ },
53
+ {
54
+ "accuracy": 0.75772,
55
+ "f1": 0.756167,
56
+ "f1_weighted": 0.756167,
57
+ "precision": 0.764456,
58
+ "precision_weighted": 0.764456,
59
+ "recall": 0.75772,
60
+ "recall_weighted": 0.75772,
61
+ "ap": 0.686138,
62
+ "ap_weighted": 0.686138
63
+ },
64
+ {
65
+ "accuracy": 0.72704,
66
+ "f1": 0.726871,
67
+ "f1_weighted": 0.726871,
68
+ "precision": 0.727604,
69
+ "precision_weighted": 0.727604,
70
+ "recall": 0.72704,
71
+ "recall_weighted": 0.72704,
72
+ "ap": 0.667766,
73
+ "ap_weighted": 0.667766
74
+ },
75
+ {
76
+ "accuracy": 0.74768,
77
+ "f1": 0.74611,
78
+ "f1_weighted": 0.74611,
79
+ "precision": 0.753962,
80
+ "precision_weighted": 0.753962,
81
+ "recall": 0.74768,
82
+ "recall_weighted": 0.74768,
83
+ "ap": 0.696635,
84
+ "ap_weighted": 0.696635
85
+ },
86
+ {
87
+ "accuracy": 0.71124,
88
+ "f1": 0.705073,
89
+ "f1_weighted": 0.705073,
90
+ "precision": 0.73052,
91
+ "precision_weighted": 0.73052,
92
+ "recall": 0.71124,
93
+ "recall_weighted": 0.71124,
94
+ "ap": 0.640232,
95
+ "ap_weighted": 0.640232
96
+ },
97
+ {
98
+ "accuracy": 0.72428,
99
+ "f1": 0.721661,
100
+ "f1_weighted": 0.721661,
101
+ "precision": 0.733051,
102
+ "precision_weighted": 0.733051,
103
+ "recall": 0.72428,
104
+ "recall_weighted": 0.72428,
105
+ "ap": 0.654269,
106
+ "ap_weighted": 0.654269
107
+ },
108
+ {
109
+ "accuracy": 0.7052,
110
+ "f1": 0.704524,
111
+ "f1_weighted": 0.704524,
112
+ "precision": 0.707096,
113
+ "precision_weighted": 0.707096,
114
+ "recall": 0.7052,
115
+ "recall_weighted": 0.7052,
116
+ "ap": 0.649162,
117
+ "ap_weighted": 0.649162
118
+ }
119
+ ],
120
+ "accuracy": 0.7391,
121
+ "f1": 0.736548,
122
+ "f1_weighted": 0.736548,
123
+ "precision": 0.747786,
124
+ "precision_weighted": 0.747786,
125
+ "recall": 0.7391,
126
+ "recall_weighted": 0.7391,
127
+ "ap": 0.678714,
128
+ "ap_weighted": 0.678714,
129
+ "main_score": 0.7391,
130
+ "hf_subset": "default",
131
+ "languages": [
132
+ "eng-Latn"
133
+ ]
134
+ }
135
+ ]
136
+ },
137
+ "evaluation_time": 356.5098555088043,
138
+ "kg_co2_emissions": null
139
+ }
results/MTOPDomainClassification.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "a76d16fae880597b9c73047b50159220a441cb54",
3
+ "task_name": "MTOPDomainClassification",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "scores_per_experiment": [
9
+ {
10
+ "accuracy": 0.930689,
11
+ "f1": 0.925808,
12
+ "f1_weighted": 0.930751,
13
+ "precision": 0.925304,
14
+ "precision_weighted": 0.932642,
15
+ "recall": 0.928221,
16
+ "recall_weighted": 0.930689,
17
+ "ap": null,
18
+ "ap_weighted": null
19
+ },
20
+ {
21
+ "accuracy": 0.942772,
22
+ "f1": 0.940072,
23
+ "f1_weighted": 0.942489,
24
+ "precision": 0.939443,
25
+ "precision_weighted": 0.943039,
26
+ "recall": 0.941619,
27
+ "recall_weighted": 0.942772,
28
+ "ap": null,
29
+ "ap_weighted": null
30
+ },
31
+ {
32
+ "accuracy": 0.920429,
33
+ "f1": 0.91604,
34
+ "f1_weighted": 0.919121,
35
+ "precision": 0.918698,
36
+ "precision_weighted": 0.920319,
37
+ "recall": 0.91624,
38
+ "recall_weighted": 0.920429,
39
+ "ap": null,
40
+ "ap_weighted": null
41
+ },
42
+ {
43
+ "accuracy": 0.928409,
44
+ "f1": 0.92513,
45
+ "f1_weighted": 0.928298,
46
+ "precision": 0.923421,
47
+ "precision_weighted": 0.93486,
48
+ "recall": 0.933284,
49
+ "recall_weighted": 0.928409,
50
+ "ap": null,
51
+ "ap_weighted": null
52
+ },
53
+ {
54
+ "accuracy": 0.926585,
55
+ "f1": 0.922983,
56
+ "f1_weighted": 0.926812,
57
+ "precision": 0.921012,
58
+ "precision_weighted": 0.928905,
59
+ "recall": 0.926841,
60
+ "recall_weighted": 0.926585,
61
+ "ap": null,
62
+ "ap_weighted": null
63
+ },
64
+ {
65
+ "accuracy": 0.929321,
66
+ "f1": 0.927184,
67
+ "f1_weighted": 0.92875,
68
+ "precision": 0.924008,
69
+ "precision_weighted": 0.930512,
70
+ "recall": 0.932269,
71
+ "recall_weighted": 0.929321,
72
+ "ap": null,
73
+ "ap_weighted": null
74
+ },
75
+ {
76
+ "accuracy": 0.919973,
77
+ "f1": 0.917008,
78
+ "f1_weighted": 0.919161,
79
+ "precision": 0.915343,
80
+ "precision_weighted": 0.921603,
81
+ "recall": 0.921312,
82
+ "recall_weighted": 0.919973,
83
+ "ap": null,
84
+ "ap_weighted": null
85
+ },
86
+ {
87
+ "accuracy": 0.933653,
88
+ "f1": 0.929426,
89
+ "f1_weighted": 0.933734,
90
+ "precision": 0.926488,
91
+ "precision_weighted": 0.934976,
92
+ "recall": 0.933667,
93
+ "recall_weighted": 0.933653,
94
+ "ap": null,
95
+ "ap_weighted": null
96
+ },
97
+ {
98
+ "accuracy": 0.925901,
99
+ "f1": 0.924229,
100
+ "f1_weighted": 0.926117,
101
+ "precision": 0.921259,
102
+ "precision_weighted": 0.928978,
103
+ "recall": 0.929757,
104
+ "recall_weighted": 0.925901,
105
+ "ap": null,
106
+ "ap_weighted": null
107
+ },
108
+ {
109
+ "accuracy": 0.932513,
110
+ "f1": 0.927476,
111
+ "f1_weighted": 0.933101,
112
+ "precision": 0.92608,
113
+ "precision_weighted": 0.9348,
114
+ "recall": 0.93007,
115
+ "recall_weighted": 0.932513,
116
+ "ap": null,
117
+ "ap_weighted": null
118
+ }
119
+ ],
120
+ "accuracy": 0.929024,
121
+ "f1": 0.925536,
122
+ "f1_weighted": 0.928834,
123
+ "precision": 0.924106,
124
+ "precision_weighted": 0.931063,
125
+ "recall": 0.929328,
126
+ "recall_weighted": 0.929024,
127
+ "ap": NaN,
128
+ "ap_weighted": NaN,
129
+ "main_score": 0.929024,
130
+ "hf_subset": "en",
131
+ "languages": [
132
+ "eng-Latn"
133
+ ]
134
+ }
135
+ ]
136
+ },
137
+ "evaluation_time": 26.848695993423462,
138
+ "kg_co2_emissions": null
139
+ }
results/MassiveIntentClassification.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "4672e20407010da34463acc759c162ca9734bca6",
3
+ "task_name": "MassiveIntentClassification",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "scores_per_experiment": [
9
+ {
10
+ "accuracy": 0.710827,
11
+ "f1": 0.686281,
12
+ "f1_weighted": 0.700845,
13
+ "precision": 0.672134,
14
+ "precision_weighted": 0.753518,
15
+ "recall": 0.780705,
16
+ "recall_weighted": 0.710827,
17
+ "ap": null,
18
+ "ap_weighted": null
19
+ },
20
+ {
21
+ "accuracy": 0.738063,
22
+ "f1": 0.713266,
23
+ "f1_weighted": 0.733315,
24
+ "precision": 0.689731,
25
+ "precision_weighted": 0.777832,
26
+ "recall": 0.809189,
27
+ "recall_weighted": 0.738063,
28
+ "ap": null,
29
+ "ap_weighted": null
30
+ },
31
+ {
32
+ "accuracy": 0.684936,
33
+ "f1": 0.649166,
34
+ "f1_weighted": 0.671955,
35
+ "precision": 0.627697,
36
+ "precision_weighted": 0.726639,
37
+ "recall": 0.75431,
38
+ "recall_weighted": 0.684936,
39
+ "ap": null,
40
+ "ap_weighted": null
41
+ },
42
+ {
43
+ "accuracy": 0.72764,
44
+ "f1": 0.692479,
45
+ "f1_weighted": 0.719029,
46
+ "precision": 0.680697,
47
+ "precision_weighted": 0.779121,
48
+ "recall": 0.783333,
49
+ "recall_weighted": 0.72764,
50
+ "ap": null,
51
+ "ap_weighted": null
52
+ },
53
+ {
54
+ "accuracy": 0.70343,
55
+ "f1": 0.675387,
56
+ "f1_weighted": 0.690133,
57
+ "precision": 0.673929,
58
+ "precision_weighted": 0.775979,
59
+ "recall": 0.773558,
60
+ "recall_weighted": 0.70343,
61
+ "ap": null,
62
+ "ap_weighted": null
63
+ },
64
+ {
65
+ "accuracy": 0.682582,
66
+ "f1": 0.658583,
67
+ "f1_weighted": 0.669777,
68
+ "precision": 0.645352,
69
+ "precision_weighted": 0.73975,
70
+ "recall": 0.762056,
71
+ "recall_weighted": 0.682582,
72
+ "ap": null,
73
+ "ap_weighted": null
74
+ },
75
+ {
76
+ "accuracy": 0.710155,
77
+ "f1": 0.686132,
78
+ "f1_weighted": 0.700469,
79
+ "precision": 0.674054,
80
+ "precision_weighted": 0.767214,
81
+ "recall": 0.784369,
82
+ "recall_weighted": 0.710155,
83
+ "ap": null,
84
+ "ap_weighted": null
85
+ },
86
+ {
87
+ "accuracy": 0.700067,
88
+ "f1": 0.674297,
89
+ "f1_weighted": 0.691119,
90
+ "precision": 0.659278,
91
+ "precision_weighted": 0.753105,
92
+ "recall": 0.778238,
93
+ "recall_weighted": 0.700067,
94
+ "ap": null,
95
+ "ap_weighted": null
96
+ },
97
+ {
98
+ "accuracy": 0.678211,
99
+ "f1": 0.663564,
100
+ "f1_weighted": 0.662266,
101
+ "precision": 0.658159,
102
+ "precision_weighted": 0.738105,
103
+ "recall": 0.765334,
104
+ "recall_weighted": 0.678211,
105
+ "ap": null,
106
+ "ap_weighted": null
107
+ },
108
+ {
109
+ "accuracy": 0.71957,
110
+ "f1": 0.695916,
111
+ "f1_weighted": 0.713896,
112
+ "precision": 0.678785,
113
+ "precision_weighted": 0.76378,
114
+ "recall": 0.787987,
115
+ "recall_weighted": 0.71957,
116
+ "ap": null,
117
+ "ap_weighted": null
118
+ }
119
+ ],
120
+ "accuracy": 0.705548,
121
+ "f1": 0.679507,
122
+ "f1_weighted": 0.69528,
123
+ "precision": 0.665981,
124
+ "precision_weighted": 0.757504,
125
+ "recall": 0.777908,
126
+ "recall_weighted": 0.705548,
127
+ "ap": NaN,
128
+ "ap_weighted": NaN,
129
+ "main_score": 0.705548,
130
+ "hf_subset": "en",
131
+ "languages": [
132
+ "eng-Latn"
133
+ ]
134
+ }
135
+ ]
136
+ },
137
+ "evaluation_time": 18.296528339385986,
138
+ "kg_co2_emissions": null
139
+ }
results/MassiveScenarioClassification.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "fad2c6e8459f9e1c45d9315f4953d921437d70f8",
3
+ "task_name": "MassiveScenarioClassification",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "scores_per_experiment": [
9
+ {
10
+ "accuracy": 0.754876,
11
+ "f1": 0.759933,
12
+ "f1_weighted": 0.756665,
13
+ "precision": 0.743929,
14
+ "precision_weighted": 0.794087,
15
+ "recall": 0.811675,
16
+ "recall_weighted": 0.754876,
17
+ "ap": null,
18
+ "ap_weighted": null
19
+ },
20
+ {
21
+ "accuracy": 0.770007,
22
+ "f1": 0.763455,
23
+ "f1_weighted": 0.7682,
24
+ "precision": 0.739999,
25
+ "precision_weighted": 0.797494,
26
+ "recall": 0.820702,
27
+ "recall_weighted": 0.770007,
28
+ "ap": null,
29
+ "ap_weighted": null
30
+ },
31
+ {
32
+ "accuracy": 0.746469,
33
+ "f1": 0.741385,
34
+ "f1_weighted": 0.74404,
35
+ "precision": 0.721267,
36
+ "precision_weighted": 0.788859,
37
+ "recall": 0.810355,
38
+ "recall_weighted": 0.746469,
39
+ "ap": null,
40
+ "ap_weighted": null
41
+ },
42
+ {
43
+ "accuracy": 0.747478,
44
+ "f1": 0.742428,
45
+ "f1_weighted": 0.747282,
46
+ "precision": 0.725834,
47
+ "precision_weighted": 0.787659,
48
+ "recall": 0.803199,
49
+ "recall_weighted": 0.747478,
50
+ "ap": null,
51
+ "ap_weighted": null
52
+ },
53
+ {
54
+ "accuracy": 0.758238,
55
+ "f1": 0.750216,
56
+ "f1_weighted": 0.753848,
57
+ "precision": 0.738617,
58
+ "precision_weighted": 0.792314,
59
+ "recall": 0.806991,
60
+ "recall_weighted": 0.758238,
61
+ "ap": null,
62
+ "ap_weighted": null
63
+ },
64
+ {
65
+ "accuracy": 0.737054,
66
+ "f1": 0.734937,
67
+ "f1_weighted": 0.73535,
68
+ "precision": 0.719189,
69
+ "precision_weighted": 0.777786,
70
+ "recall": 0.794776,
71
+ "recall_weighted": 0.737054,
72
+ "ap": null,
73
+ "ap_weighted": null
74
+ },
75
+ {
76
+ "accuracy": 0.750841,
77
+ "f1": 0.749553,
78
+ "f1_weighted": 0.751482,
79
+ "precision": 0.73113,
80
+ "precision_weighted": 0.793698,
81
+ "recall": 0.813341,
82
+ "recall_weighted": 0.750841,
83
+ "ap": null,
84
+ "ap_weighted": null
85
+ },
86
+ {
87
+ "accuracy": 0.752858,
88
+ "f1": 0.749056,
89
+ "f1_weighted": 0.755294,
90
+ "precision": 0.730356,
91
+ "precision_weighted": 0.785254,
92
+ "recall": 0.79926,
93
+ "recall_weighted": 0.752858,
94
+ "ap": null,
95
+ "ap_weighted": null
96
+ },
97
+ {
98
+ "accuracy": 0.746469,
99
+ "f1": 0.746646,
100
+ "f1_weighted": 0.743745,
101
+ "precision": 0.730467,
102
+ "precision_weighted": 0.780117,
103
+ "recall": 0.805504,
104
+ "recall_weighted": 0.746469,
105
+ "ap": null,
106
+ "ap_weighted": null
107
+ },
108
+ {
109
+ "accuracy": 0.745797,
110
+ "f1": 0.740494,
111
+ "f1_weighted": 0.747993,
112
+ "precision": 0.724341,
113
+ "precision_weighted": 0.789005,
114
+ "recall": 0.800835,
115
+ "recall_weighted": 0.745797,
116
+ "ap": null,
117
+ "ap_weighted": null
118
+ }
119
+ ],
120
+ "accuracy": 0.751009,
121
+ "f1": 0.74781,
122
+ "f1_weighted": 0.75039,
123
+ "precision": 0.730513,
124
+ "precision_weighted": 0.788627,
125
+ "recall": 0.806664,
126
+ "recall_weighted": 0.751009,
127
+ "ap": NaN,
128
+ "ap_weighted": NaN,
129
+ "main_score": 0.751009,
130
+ "hf_subset": "en",
131
+ "languages": [
132
+ "eng-Latn"
133
+ ]
134
+ }
135
+ ]
136
+ },
137
+ "evaluation_time": 11.3934006690979,
138
+ "kg_co2_emissions": null
139
+ }
results/MedrxivClusteringP2P.v2.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "e7a26af6f3ae46b30dde8737f02c07b1505bcc73",
3
+ "task_name": "MedrxivClusteringP2P.v2",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "v_measures": {
9
+ "Level 0": [
10
+ 0.377805,
11
+ 0.359674,
12
+ 0.364929,
13
+ 0.359207,
14
+ 0.352883,
15
+ 0.349402,
16
+ 0.348864,
17
+ 0.370065,
18
+ 0.375078,
19
+ 0.365294
20
+ ]
21
+ },
22
+ "v_measure": 0.36232,
23
+ "v_measure_std": 0.009653,
24
+ "main_score": 0.36232,
25
+ "hf_subset": "default",
26
+ "languages": [
27
+ "eng-Latn"
28
+ ]
29
+ }
30
+ ]
31
+ },
32
+ "evaluation_time": 25.822656869888306,
33
+ "kg_co2_emissions": null
34
+ }
results/MedrxivClusteringS2S.v2.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "35191c8c0dca72d8ff3efcd72aa802307d469663",
3
+ "task_name": "MedrxivClusteringS2S.v2",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "v_measures": {
9
+ "Level 0": [
10
+ 0.35865,
11
+ 0.359604,
12
+ 0.350533,
13
+ 0.352652,
14
+ 0.335118,
15
+ 0.340107,
16
+ 0.343553,
17
+ 0.344392,
18
+ 0.357347,
19
+ 0.366842
20
+ ]
21
+ },
22
+ "v_measure": 0.35088,
23
+ "v_measure_std": 0.009469,
24
+ "main_score": 0.35088,
25
+ "hf_subset": "default",
26
+ "languages": [
27
+ "eng-Latn"
28
+ ]
29
+ }
30
+ ]
31
+ },
32
+ "evaluation_time": 3.8875985145568848,
33
+ "kg_co2_emissions": null
34
+ }
results/MindSmallReranking.json ADDED
@@ -0,0 +1,251 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "227478e3235572039f4f7661840e059f31ef6eb1",
3
+ "task_name": "MindSmallReranking",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "ndcg_at_1": 0.13797,
9
+ "ndcg_at_3": 0.21241,
10
+ "ndcg_at_5": 0.25804,
11
+ "ndcg_at_10": 0.32027,
12
+ "ndcg_at_20": 0.37273,
13
+ "ndcg_at_100": 0.43496,
14
+ "ndcg_at_1000": 0.43832,
15
+ "map_at_1": 0.10526,
16
+ "map_at_3": 0.17504,
17
+ "map_at_5": 0.20229,
18
+ "map_at_10": 0.23024,
19
+ "map_at_20": 0.24746,
20
+ "map_at_100": 0.26086,
21
+ "map_at_1000": 0.26129,
22
+ "recall_at_1": 0.10526,
23
+ "recall_at_3": 0.26154,
24
+ "recall_at_5": 0.37059,
25
+ "recall_at_10": 0.54664,
26
+ "recall_at_20": 0.7251,
27
+ "recall_at_100": 0.98378,
28
+ "recall_at_1000": 1.0,
29
+ "accuracy": 0.10526,
30
+ "precision_at_1": 0.13797,
31
+ "precision_at_3": 0.11675,
32
+ "precision_at_5": 0.10174,
33
+ "precision_at_10": 0.079,
34
+ "precision_at_20": 0.05607,
35
+ "precision_at_100": 0.01767,
36
+ "precision_at_1000": 0.00183,
37
+ "mrr_at_1": 0.13797,
38
+ "mrr_at_3": 0.221127,
39
+ "mrr_at_5": 0.250337,
40
+ "mrr_at_10": 0.275951,
41
+ "mrr_at_20": 0.287941,
42
+ "mrr_at_100": 0.293167,
43
+ "mrr_at_1000": 0.293211,
44
+ "nauc_ndcg_at_1_max": -0.080841,
45
+ "nauc_ndcg_at_1_std": 0.024292,
46
+ "nauc_ndcg_at_1_diff1": 0.138468,
47
+ "nauc_ndcg_at_3_max": -0.181703,
48
+ "nauc_ndcg_at_3_std": -0.008494,
49
+ "nauc_ndcg_at_3_diff1": 0.143634,
50
+ "nauc_ndcg_at_5_max": -0.216759,
51
+ "nauc_ndcg_at_5_std": -0.015709,
52
+ "nauc_ndcg_at_5_diff1": 0.141822,
53
+ "nauc_ndcg_at_10_max": -0.252302,
54
+ "nauc_ndcg_at_10_std": -0.020766,
55
+ "nauc_ndcg_at_10_diff1": 0.140598,
56
+ "nauc_ndcg_at_20_max": -0.260966,
57
+ "nauc_ndcg_at_20_std": -0.019277,
58
+ "nauc_ndcg_at_20_diff1": 0.139796,
59
+ "nauc_ndcg_at_100_max": -0.199958,
60
+ "nauc_ndcg_at_100_std": -0.007378,
61
+ "nauc_ndcg_at_100_diff1": 0.135835,
62
+ "nauc_ndcg_at_1000_max": -0.188946,
63
+ "nauc_ndcg_at_1000_std": -0.005857,
64
+ "nauc_ndcg_at_1000_diff1": 0.135192,
65
+ "nauc_map_at_1_max": -0.146047,
66
+ "nauc_map_at_1_std": 0.00283,
67
+ "nauc_map_at_1_diff1": 0.164118,
68
+ "nauc_map_at_3_max": -0.19319,
69
+ "nauc_map_at_3_std": -0.011653,
70
+ "nauc_map_at_3_diff1": 0.154271,
71
+ "nauc_map_at_5_max": -0.210554,
72
+ "nauc_map_at_5_std": -0.014481,
73
+ "nauc_map_at_5_diff1": 0.151202,
74
+ "nauc_map_at_10_max": -0.225351,
75
+ "nauc_map_at_10_std": -0.015752,
76
+ "nauc_map_at_10_diff1": 0.149613,
77
+ "nauc_map_at_20_max": -0.226452,
78
+ "nauc_map_at_20_std": -0.014523,
79
+ "nauc_map_at_20_diff1": 0.148744,
80
+ "nauc_map_at_100_max": -0.214078,
81
+ "nauc_map_at_100_std": -0.011849,
82
+ "nauc_map_at_100_diff1": 0.14765,
83
+ "nauc_map_at_1000_max": -0.212928,
84
+ "nauc_map_at_1000_std": -0.011684,
85
+ "nauc_map_at_1000_diff1": 0.147593,
86
+ "nauc_recall_at_1_max": -0.146047,
87
+ "nauc_recall_at_1_std": 0.00283,
88
+ "nauc_recall_at_1_diff1": 0.164118,
89
+ "nauc_recall_at_3_max": -0.225285,
90
+ "nauc_recall_at_3_std": -0.024226,
91
+ "nauc_recall_at_3_diff1": 0.140466,
92
+ "nauc_recall_at_5_max": -0.274423,
93
+ "nauc_recall_at_5_std": -0.034792,
94
+ "nauc_recall_at_5_diff1": 0.131684,
95
+ "nauc_recall_at_10_max": -0.360767,
96
+ "nauc_recall_at_10_std": -0.04966,
97
+ "nauc_recall_at_10_diff1": 0.126071,
98
+ "nauc_recall_at_20_max": -0.454167,
99
+ "nauc_recall_at_20_std": -0.059684,
100
+ "nauc_recall_at_20_diff1": 0.124668,
101
+ "nauc_recall_at_100_max": -0.777894,
102
+ "nauc_recall_at_100_std": -0.089707,
103
+ "nauc_recall_at_100_diff1": 0.131562,
104
+ "nauc_recall_at_1000_max": -0.663492,
105
+ "nauc_recall_at_1000_std": 0.26536,
106
+ "nauc_recall_at_1000_diff1": 0.211204,
107
+ "nauc_precision_at_1_max": -0.080841,
108
+ "nauc_precision_at_1_std": 0.024292,
109
+ "nauc_precision_at_1_diff1": 0.138468,
110
+ "nauc_precision_at_3_max": -0.1417,
111
+ "nauc_precision_at_3_std": 0.007655,
112
+ "nauc_precision_at_3_diff1": 0.111485,
113
+ "nauc_precision_at_5_max": -0.163184,
114
+ "nauc_precision_at_5_std": 0.004693,
115
+ "nauc_precision_at_5_diff1": 0.092409,
116
+ "nauc_precision_at_10_max": -0.148818,
117
+ "nauc_precision_at_10_std": 0.007789,
118
+ "nauc_precision_at_10_diff1": 0.053076,
119
+ "nauc_precision_at_20_max": -0.049221,
120
+ "nauc_precision_at_20_std": 0.023456,
121
+ "nauc_precision_at_20_diff1": 0.003135,
122
+ "nauc_precision_at_100_max": 0.238253,
123
+ "nauc_precision_at_100_std": 0.051859,
124
+ "nauc_precision_at_100_diff1": -0.070209,
125
+ "nauc_precision_at_1000_max": 0.267382,
126
+ "nauc_precision_at_1000_std": 0.05417,
127
+ "nauc_precision_at_1000_diff1": -0.073075,
128
+ "nauc_mrr_at_1_max": -0.080841,
129
+ "nauc_mrr_at_1_std": 0.024292,
130
+ "nauc_mrr_at_1_diff1": 0.138468,
131
+ "nauc_mrr_at_3_max": -0.126867,
132
+ "nauc_mrr_at_3_std": 0.008045,
133
+ "nauc_mrr_at_3_diff1": 0.129913,
134
+ "nauc_mrr_at_5_max": -0.14205,
135
+ "nauc_mrr_at_5_std": 0.004575,
136
+ "nauc_mrr_at_5_diff1": 0.128157,
137
+ "nauc_mrr_at_10_max": -0.152516,
138
+ "nauc_mrr_at_10_std": 0.00273,
139
+ "nauc_mrr_at_10_diff1": 0.128082,
140
+ "nauc_mrr_at_20_max": -0.152624,
141
+ "nauc_mrr_at_20_std": 0.003079,
142
+ "nauc_mrr_at_20_diff1": 0.12863,
143
+ "nauc_mrr_at_100_max": -0.148748,
144
+ "nauc_mrr_at_100_std": 0.003913,
145
+ "nauc_mrr_at_100_diff1": 0.128945,
146
+ "nauc_mrr_at_1000_max": -0.148643,
147
+ "nauc_mrr_at_1000_std": 0.003928,
148
+ "nauc_mrr_at_1000_diff1": 0.128943,
149
+ "cv_recall_at_1": 0.13797,
150
+ "cv_recall_at_3": 0.3314,
151
+ "cv_recall_at_5": 0.45994,
152
+ "cv_recall_at_10": 0.65201,
153
+ "cv_recall_at_20": 0.82206,
154
+ "cv_recall_at_100": 0.99452,
155
+ "cv_recall_at_1000": 1.0,
156
+ "max_over_subqueries_ndcg_at_1": 0.18157,
157
+ "max_over_subqueries_ndcg_at_3": 0.2781,
158
+ "max_over_subqueries_ndcg_at_5": 0.32778,
159
+ "max_over_subqueries_ndcg_at_10": 0.38893,
160
+ "max_over_subqueries_ndcg_at_20": 0.43524,
161
+ "max_over_subqueries_ndcg_at_100": 0.47921,
162
+ "max_over_subqueries_ndcg_at_1000": 0.48093,
163
+ "max_over_subqueries_map_at_1": 0.15223,
164
+ "max_over_subqueries_map_at_3": 0.23877,
165
+ "max_over_subqueries_map_at_5": 0.26808,
166
+ "max_over_subqueries_map_at_10": 0.29544,
167
+ "max_over_subqueries_map_at_20": 0.31057,
168
+ "max_over_subqueries_map_at_100": 0.31976,
169
+ "max_over_subqueries_map_at_1000": 0.31995,
170
+ "max_over_subqueries_recall_at_1": 0.15223,
171
+ "max_over_subqueries_recall_at_3": 0.34521,
172
+ "max_over_subqueries_recall_at_5": 0.46271,
173
+ "max_over_subqueries_recall_at_10": 0.6379,
174
+ "max_over_subqueries_recall_at_20": 0.79955,
175
+ "max_over_subqueries_recall_at_100": 0.9909,
176
+ "max_over_subqueries_recall_at_1000": 0.99999,
177
+ "max_over_subqueries_accuracy": 0.15223,
178
+ "max_over_subqueries_precision_at_1": 0.18157,
179
+ "max_over_subqueries_precision_at_3": 0.14099,
180
+ "max_over_subqueries_precision_at_5": 0.11615,
181
+ "max_over_subqueries_precision_at_10": 0.08346,
182
+ "max_over_subqueries_precision_at_20": 0.05512,
183
+ "max_over_subqueries_precision_at_100": 0.01496,
184
+ "max_over_subqueries_precision_at_1000": 0.00152,
185
+ "max_over_subqueries_mrr_at_1_max": -0.096401,
186
+ "max_over_subqueries_mrr_at_1_std": 0.002808,
187
+ "max_over_subqueries_mrr_at_1_diff1": 0.127174,
188
+ "max_over_subqueries_mrr_at_3_max": -0.151284,
189
+ "max_over_subqueries_mrr_at_3_std": -0.022115,
190
+ "max_over_subqueries_mrr_at_3_diff1": 0.083457,
191
+ "max_over_subqueries_mrr_at_5_max": -0.15603,
192
+ "max_over_subqueries_mrr_at_5_std": -0.021423,
193
+ "max_over_subqueries_mrr_at_5_diff1": 0.063603,
194
+ "max_over_subqueries_mrr_at_10_max": -0.100349,
195
+ "max_over_subqueries_mrr_at_10_std": 0.000562,
196
+ "max_over_subqueries_mrr_at_10_diff1": 0.034754,
197
+ "max_over_subqueries_mrr_at_20_max": 0.053805,
198
+ "max_over_subqueries_mrr_at_20_std": 0.05231,
199
+ "max_over_subqueries_mrr_at_20_diff1": 0.012975,
200
+ "max_over_subqueries_mrr_at_100_max": 0.363688,
201
+ "max_over_subqueries_mrr_at_100_std": 0.151404,
202
+ "max_over_subqueries_mrr_at_100_diff1": -0.003812,
203
+ "max_over_subqueries_mrr_at_1000_max": 0.383704,
204
+ "max_over_subqueries_mrr_at_1000_std": 0.155746,
205
+ "max_over_subqueries_mrr_at_1000_diff1": -0.001695,
206
+ "max_over_subqueries_mrr_at_1": 0.181567,
207
+ "max_over_subqueries_mrr_at_3": 0.277909,
208
+ "max_over_subqueries_mrr_at_5": 0.307396,
209
+ "max_over_subqueries_mrr_at_10": 0.33153,
210
+ "max_over_subqueries_mrr_at_20": 0.342013,
211
+ "max_over_subqueries_mrr_at_100": 0.346119,
212
+ "max_over_subqueries_mrr_at_1000": 0.34615,
213
+ "max_over_subqueries_nauc_mrr_at_1_max": -0.096401,
214
+ "max_over_subqueries_nauc_mrr_at_1_std": 0.002808,
215
+ "max_over_subqueries_nauc_mrr_at_1_diff1": 0.127174,
216
+ "max_over_subqueries_nauc_mrr_at_3_max": -0.137626,
217
+ "max_over_subqueries_nauc_mrr_at_3_std": -0.018024,
218
+ "max_over_subqueries_nauc_mrr_at_3_diff1": 0.109109,
219
+ "max_over_subqueries_nauc_mrr_at_5_max": -0.148111,
220
+ "max_over_subqueries_nauc_mrr_at_5_std": -0.021639,
221
+ "max_over_subqueries_nauc_mrr_at_5_diff1": 0.106917,
222
+ "max_over_subqueries_nauc_mrr_at_10_max": -0.153997,
223
+ "max_over_subqueries_nauc_mrr_at_10_std": -0.023228,
224
+ "max_over_subqueries_nauc_mrr_at_10_diff1": 0.106383,
225
+ "max_over_subqueries_nauc_mrr_at_20_max": -0.152713,
226
+ "max_over_subqueries_nauc_mrr_at_20_std": -0.022604,
227
+ "max_over_subqueries_nauc_mrr_at_20_diff1": 0.107456,
228
+ "max_over_subqueries_nauc_mrr_at_100_max": -0.150034,
229
+ "max_over_subqueries_nauc_mrr_at_100_std": -0.021563,
230
+ "max_over_subqueries_nauc_mrr_at_100_diff1": 0.108132,
231
+ "max_over_subqueries_nauc_mrr_at_1000_max": -0.149992,
232
+ "max_over_subqueries_nauc_mrr_at_1000_std": -0.02156,
233
+ "max_over_subqueries_nauc_mrr_at_1000_diff1": 0.108142,
234
+ "max_over_subqueries_cv_recall_at_1": 0.18157,
235
+ "max_over_subqueries_cv_recall_at_3": 0.40389,
236
+ "max_over_subqueries_cv_recall_at_5": 0.53341,
237
+ "max_over_subqueries_cv_recall_at_10": 0.71386,
238
+ "max_over_subqueries_cv_recall_at_20": 0.86189,
239
+ "max_over_subqueries_cv_recall_at_100": 0.99621,
240
+ "max_over_subqueries_cv_recall_at_1000": 0.99999,
241
+ "main_score": 0.31995,
242
+ "hf_subset": "default",
243
+ "languages": [
244
+ "eng-Latn"
245
+ ]
246
+ }
247
+ ]
248
+ },
249
+ "evaluation_time": 3442.481809616089,
250
+ "kg_co2_emissions": null
251
+ }
results/SCIDOCS.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "f8c2fcf00f625baaa80f62ec5bd9e1fff3b8ae88",
3
+ "task_name": "SCIDOCS",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "ndcg_at_1": 0.229,
9
+ "ndcg_at_3": 0.19177,
10
+ "ndcg_at_5": 0.16985,
11
+ "ndcg_at_10": 0.20397,
12
+ "ndcg_at_20": 0.23318,
13
+ "ndcg_at_100": 0.28234,
14
+ "ndcg_at_1000": 0.33678,
15
+ "map_at_1": 0.04628,
16
+ "map_at_3": 0.08519,
17
+ "map_at_5": 0.1041,
18
+ "map_at_10": 0.12123,
19
+ "map_at_20": 0.13279,
20
+ "map_at_100": 0.14238,
21
+ "map_at_1000": 0.14547,
22
+ "recall_at_1": 0.04628,
23
+ "recall_at_3": 0.10978,
24
+ "recall_at_5": 0.15358,
25
+ "recall_at_10": 0.21657,
26
+ "recall_at_20": 0.28518,
27
+ "recall_at_100": 0.44645,
28
+ "recall_at_1000": 0.7127,
29
+ "accuracy": 0.04628,
30
+ "precision_at_1": 0.229,
31
+ "precision_at_3": 0.181,
32
+ "precision_at_5": 0.1518,
33
+ "precision_at_10": 0.1068,
34
+ "precision_at_20": 0.07025,
35
+ "precision_at_100": 0.02196,
36
+ "precision_at_1000": 0.00351,
37
+ "mrr_at_1": 0.229,
38
+ "mrr_at_3": 0.308833,
39
+ "mrr_at_5": 0.326533,
40
+ "mrr_at_10": 0.34042,
41
+ "mrr_at_20": 0.346252,
42
+ "mrr_at_100": 0.350634,
43
+ "mrr_at_1000": 0.351165,
44
+ "nauc_ndcg_at_1_max": 0.201567,
45
+ "nauc_ndcg_at_1_std": 0.025003,
46
+ "nauc_ndcg_at_1_diff1": 0.249343,
47
+ "nauc_ndcg_at_3_max": 0.244581,
48
+ "nauc_ndcg_at_3_std": 0.083544,
49
+ "nauc_ndcg_at_3_diff1": 0.248671,
50
+ "nauc_ndcg_at_5_max": 0.271376,
51
+ "nauc_ndcg_at_5_std": 0.127383,
52
+ "nauc_ndcg_at_5_diff1": 0.248297,
53
+ "nauc_ndcg_at_10_max": 0.283017,
54
+ "nauc_ndcg_at_10_std": 0.166271,
55
+ "nauc_ndcg_at_10_diff1": 0.224542,
56
+ "nauc_ndcg_at_20_max": 0.28319,
57
+ "nauc_ndcg_at_20_std": 0.195918,
58
+ "nauc_ndcg_at_20_diff1": 0.215699,
59
+ "nauc_ndcg_at_100_max": 0.29645,
60
+ "nauc_ndcg_at_100_std": 0.251027,
61
+ "nauc_ndcg_at_100_diff1": 0.220365,
62
+ "nauc_ndcg_at_1000_max": 0.291802,
63
+ "nauc_ndcg_at_1000_std": 0.25888,
64
+ "nauc_ndcg_at_1000_diff1": 0.226164,
65
+ "nauc_map_at_1_max": 0.205601,
66
+ "nauc_map_at_1_std": 0.025056,
67
+ "nauc_map_at_1_diff1": 0.252645,
68
+ "nauc_map_at_3_max": 0.235191,
69
+ "nauc_map_at_3_std": 0.060006,
70
+ "nauc_map_at_3_diff1": 0.251343,
71
+ "nauc_map_at_5_max": 0.260652,
72
+ "nauc_map_at_5_std": 0.099773,
73
+ "nauc_map_at_5_diff1": 0.250725,
74
+ "nauc_map_at_10_max": 0.271354,
75
+ "nauc_map_at_10_std": 0.133786,
76
+ "nauc_map_at_10_diff1": 0.234156,
77
+ "nauc_map_at_20_max": 0.27077,
78
+ "nauc_map_at_20_std": 0.154086,
79
+ "nauc_map_at_20_diff1": 0.226082,
80
+ "nauc_map_at_100_max": 0.277889,
81
+ "nauc_map_at_100_std": 0.176531,
82
+ "nauc_map_at_100_diff1": 0.227675,
83
+ "nauc_map_at_1000_max": 0.27778,
84
+ "nauc_map_at_1000_std": 0.178953,
85
+ "nauc_map_at_1000_diff1": 0.228126,
86
+ "nauc_recall_at_1_max": 0.205601,
87
+ "nauc_recall_at_1_std": 0.025056,
88
+ "nauc_recall_at_1_diff1": 0.252645,
89
+ "nauc_recall_at_3_max": 0.259799,
90
+ "nauc_recall_at_3_std": 0.103228,
91
+ "nauc_recall_at_3_diff1": 0.242304,
92
+ "nauc_recall_at_5_max": 0.286247,
93
+ "nauc_recall_at_5_std": 0.167583,
94
+ "nauc_recall_at_5_diff1": 0.229927,
95
+ "nauc_recall_at_10_max": 0.288616,
96
+ "nauc_recall_at_10_std": 0.225986,
97
+ "nauc_recall_at_10_diff1": 0.171647,
98
+ "nauc_recall_at_20_max": 0.271409,
99
+ "nauc_recall_at_20_std": 0.270025,
100
+ "nauc_recall_at_20_diff1": 0.148733,
101
+ "nauc_recall_at_100_max": 0.272811,
102
+ "nauc_recall_at_100_std": 0.382225,
103
+ "nauc_recall_at_100_diff1": 0.14319,
104
+ "nauc_recall_at_1000_max": 0.21325,
105
+ "nauc_recall_at_1000_std": 0.413189,
106
+ "nauc_recall_at_1000_diff1": 0.128172,
107
+ "nauc_precision_at_1_max": 0.201567,
108
+ "nauc_precision_at_1_std": 0.025003,
109
+ "nauc_precision_at_1_diff1": 0.249343,
110
+ "nauc_precision_at_3_max": 0.259355,
111
+ "nauc_precision_at_3_std": 0.10383,
112
+ "nauc_precision_at_3_diff1": 0.243294,
113
+ "nauc_precision_at_5_max": 0.285931,
114
+ "nauc_precision_at_5_std": 0.167941,
115
+ "nauc_precision_at_5_diff1": 0.231946,
116
+ "nauc_precision_at_10_max": 0.291145,
117
+ "nauc_precision_at_10_std": 0.224609,
118
+ "nauc_precision_at_10_diff1": 0.174244,
119
+ "nauc_precision_at_20_max": 0.274894,
120
+ "nauc_precision_at_20_std": 0.268659,
121
+ "nauc_precision_at_20_diff1": 0.15295,
122
+ "nauc_precision_at_100_max": 0.27833,
123
+ "nauc_precision_at_100_std": 0.378446,
124
+ "nauc_precision_at_100_diff1": 0.146166,
125
+ "nauc_precision_at_1000_max": 0.218799,
126
+ "nauc_precision_at_1000_std": 0.396878,
127
+ "nauc_precision_at_1000_diff1": 0.128176,
128
+ "nauc_mrr_at_1_max": 0.201567,
129
+ "nauc_mrr_at_1_std": 0.025003,
130
+ "nauc_mrr_at_1_diff1": 0.249343,
131
+ "nauc_mrr_at_3_max": 0.24346,
132
+ "nauc_mrr_at_3_std": 0.08929,
133
+ "nauc_mrr_at_3_diff1": 0.249529,
134
+ "nauc_mrr_at_5_max": 0.248429,
135
+ "nauc_mrr_at_5_std": 0.099991,
136
+ "nauc_mrr_at_5_diff1": 0.250386,
137
+ "nauc_mrr_at_10_max": 0.249876,
138
+ "nauc_mrr_at_10_std": 0.107423,
139
+ "nauc_mrr_at_10_diff1": 0.247606,
140
+ "nauc_mrr_at_20_max": 0.249592,
141
+ "nauc_mrr_at_20_std": 0.109629,
142
+ "nauc_mrr_at_20_diff1": 0.24638,
143
+ "nauc_mrr_at_100_max": 0.24894,
144
+ "nauc_mrr_at_100_std": 0.109041,
145
+ "nauc_mrr_at_100_diff1": 0.247362,
146
+ "nauc_mrr_at_1000_max": 0.248781,
147
+ "nauc_mrr_at_1000_std": 0.108737,
148
+ "nauc_mrr_at_1000_diff1": 0.247405,
149
+ "cv_recall_at_1": 0.229,
150
+ "cv_recall_at_3": 0.413,
151
+ "cv_recall_at_5": 0.491,
152
+ "cv_recall_at_10": 0.597,
153
+ "cv_recall_at_20": 0.683,
154
+ "cv_recall_at_100": 0.861,
155
+ "cv_recall_at_1000": 0.977,
156
+ "main_score": 0.20397,
157
+ "hf_subset": "default",
158
+ "languages": [
159
+ "eng-Latn"
160
+ ]
161
+ }
162
+ ]
163
+ },
164
+ "evaluation_time": 296.4552068710327,
165
+ "kg_co2_emissions": null
166
+ }
results/SICK-R.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "20a6d6f312dd54037fe07a32d58e5e168867909d",
3
+ "task_name": "SICK-R",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "pearson": 0.818956,
9
+ "spearman": 0.755086,
10
+ "cosine_pearson": 0.818956,
11
+ "cosine_spearman": 0.755086,
12
+ "manhattan_pearson": 0.794581,
13
+ "manhattan_spearman": 0.754753,
14
+ "euclidean_pearson": 0.794736,
15
+ "euclidean_spearman": 0.755086,
16
+ "main_score": 0.755086,
17
+ "hf_subset": "default",
18
+ "languages": [
19
+ "eng-Latn"
20
+ ]
21
+ }
22
+ ]
23
+ },
24
+ "evaluation_time": 14.770185232162476,
25
+ "kg_co2_emissions": null
26
+ }
results/STS12.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "a0d554a64d88156834ff5ae9920b964011b16384",
3
+ "task_name": "STS12",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "pearson": 0.747066,
9
+ "spearman": 0.671139,
10
+ "cosine_pearson": 0.747066,
11
+ "cosine_spearman": 0.671139,
12
+ "manhattan_pearson": 0.711023,
13
+ "manhattan_spearman": 0.671594,
14
+ "euclidean_pearson": 0.710487,
15
+ "euclidean_spearman": 0.671139,
16
+ "main_score": 0.671139,
17
+ "hf_subset": "default",
18
+ "languages": [
19
+ "eng-Latn"
20
+ ]
21
+ }
22
+ ]
23
+ },
24
+ "evaluation_time": 6.07265830039978,
25
+ "kg_co2_emissions": null
26
+ }
results/STS13.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "7e90230a92c190f1bf69ae9002b8cea547a64cca",
3
+ "task_name": "STS13",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "pearson": 0.787439,
9
+ "spearman": 0.794128,
10
+ "cosine_pearson": 0.787439,
11
+ "cosine_spearman": 0.794128,
12
+ "manhattan_pearson": 0.792422,
13
+ "manhattan_spearman": 0.793896,
14
+ "euclidean_pearson": 0.792596,
15
+ "euclidean_spearman": 0.794128,
16
+ "main_score": 0.794128,
17
+ "hf_subset": "default",
18
+ "languages": [
19
+ "eng-Latn"
20
+ ]
21
+ }
22
+ ]
23
+ },
24
+ "evaluation_time": 2.542609930038452,
25
+ "kg_co2_emissions": null
26
+ }
results/STS14.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "6031580fec1f6af667f0bd2da0a551cf4f0b2375",
3
+ "task_name": "STS14",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "pearson": 0.778421,
9
+ "spearman": 0.730703,
10
+ "cosine_pearson": 0.778421,
11
+ "cosine_spearman": 0.730702,
12
+ "manhattan_pearson": 0.76257,
13
+ "manhattan_spearman": 0.730385,
14
+ "euclidean_pearson": 0.762853,
15
+ "euclidean_spearman": 0.730703,
16
+ "main_score": 0.730702,
17
+ "hf_subset": "default",
18
+ "languages": [
19
+ "eng-Latn"
20
+ ]
21
+ }
22
+ ]
23
+ },
24
+ "evaluation_time": 6.641091346740723,
25
+ "kg_co2_emissions": null
26
+ }
results/STS15.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "ae752c7c21bf194d8b67fd573edf7ae58183cbe3",
3
+ "task_name": "STS15",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "pearson": 0.82503,
9
+ "spearman": 0.832935,
10
+ "cosine_pearson": 0.82503,
11
+ "cosine_spearman": 0.832935,
12
+ "manhattan_pearson": 0.827663,
13
+ "manhattan_spearman": 0.833017,
14
+ "euclidean_pearson": 0.827557,
15
+ "euclidean_spearman": 0.832935,
16
+ "main_score": 0.832935,
17
+ "hf_subset": "default",
18
+ "languages": [
19
+ "eng-Latn"
20
+ ]
21
+ }
22
+ ]
23
+ },
24
+ "evaluation_time": 5.315732002258301,
25
+ "kg_co2_emissions": null
26
+ }
results/STS17.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "faeb762787bd10488a50c8b5be4a3b82e411949c",
3
+ "task_name": "STS17",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "pearson": 0.850936,
9
+ "spearman": 0.863504,
10
+ "cosine_pearson": 0.850936,
11
+ "cosine_spearman": 0.863504,
12
+ "manhattan_pearson": 0.858119,
13
+ "manhattan_spearman": 0.863436,
14
+ "euclidean_pearson": 0.857847,
15
+ "euclidean_spearman": 0.863504,
16
+ "main_score": 0.863504,
17
+ "hf_subset": "en-en",
18
+ "languages": [
19
+ "eng-Latn"
20
+ ]
21
+ }
22
+ ]
23
+ },
24
+ "evaluation_time": 0.366685152053833,
25
+ "kg_co2_emissions": null
26
+ }
results/STS22.v2.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "d31f33a128469b20e357535c39b82fb3c3f6f2bd",
3
+ "task_name": "STS22.v2",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "pearson": 0.682427,
9
+ "spearman": 0.682858,
10
+ "cosine_pearson": 0.682427,
11
+ "cosine_spearman": 0.682858,
12
+ "manhattan_pearson": 0.695294,
13
+ "manhattan_spearman": 0.678261,
14
+ "euclidean_pearson": 0.697765,
15
+ "euclidean_spearman": 0.682858,
16
+ "main_score": 0.682858,
17
+ "hf_subset": "en",
18
+ "languages": [
19
+ "eng-Latn"
20
+ ]
21
+ }
22
+ ]
23
+ },
24
+ "evaluation_time": 6.849907875061035,
25
+ "kg_co2_emissions": null
26
+ }
results/STSBenchmark.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "b0fddb56ed78048fa8b90373c8a3cfc37b684831",
3
+ "task_name": "STSBenchmark",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "pearson": 0.80547,
9
+ "spearman": 0.800609,
10
+ "cosine_pearson": 0.80547,
11
+ "cosine_spearman": 0.800609,
12
+ "manhattan_pearson": 0.807637,
13
+ "manhattan_spearman": 0.800915,
14
+ "euclidean_pearson": 0.807593,
15
+ "euclidean_spearman": 0.800609,
16
+ "main_score": 0.800609,
17
+ "hf_subset": "default",
18
+ "languages": [
19
+ "eng-Latn"
20
+ ]
21
+ }
22
+ ]
23
+ },
24
+ "evaluation_time": 2.4762179851531982,
25
+ "kg_co2_emissions": null
26
+ }
results/SprintDuplicateQuestions.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46",
3
+ "task_name": "SprintDuplicateQuestions",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "similarity_accuracy": 0.998139,
9
+ "similarity_f1": 0.906838,
10
+ "similarity_precision": 0.898821,
11
+ "similarity_recall": 0.915,
12
+ "similarity_ap": 0.946636,
13
+ "cosine_accuracy": 0.998139,
14
+ "cosine_f1": 0.906838,
15
+ "cosine_precision": 0.898821,
16
+ "cosine_recall": 0.915,
17
+ "cosine_ap": 0.946636,
18
+ "manhattan_accuracy": 0.998119,
19
+ "manhattan_f1": 0.905492,
20
+ "manhattan_precision": 0.89618,
21
+ "manhattan_recall": 0.915,
22
+ "manhattan_ap": 0.946595,
23
+ "euclidean_accuracy": 0.998139,
24
+ "euclidean_f1": 0.906838,
25
+ "euclidean_precision": 0.898821,
26
+ "euclidean_recall": 0.915,
27
+ "euclidean_ap": 0.946636,
28
+ "dot_accuracy": 0.998139,
29
+ "dot_f1": 0.906838,
30
+ "dot_precision": 0.898821,
31
+ "dot_recall": 0.915,
32
+ "dot_ap": 0.946636,
33
+ "max_accuracy": 0.998139,
34
+ "max_f1": 0.906838,
35
+ "max_precision": 0.898821,
36
+ "max_recall": 0.915,
37
+ "max_ap": 0.946636,
38
+ "main_score": 0.946636,
39
+ "hf_subset": "default",
40
+ "languages": [
41
+ "eng-Latn"
42
+ ]
43
+ }
44
+ ]
45
+ },
46
+ "evaluation_time": 175.06178259849548,
47
+ "kg_co2_emissions": null
48
+ }
results/StackExchangeClustering.v2.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "6cbc1f7b2bc0622f2e39d2c77fa502909748c259",
3
+ "task_name": "StackExchangeClustering.v2",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "v_measures": {
9
+ "Level 0": [
10
+ 0.608624,
11
+ 0.614347,
12
+ 0.610241,
13
+ 0.614611,
14
+ 0.618373,
15
+ 0.616131,
16
+ 0.605268,
17
+ 0.614997,
18
+ 0.608024,
19
+ 0.621991
20
+ ]
21
+ },
22
+ "v_measure": 0.613261,
23
+ "v_measure_std": 0.004884,
24
+ "main_score": 0.613261,
25
+ "hf_subset": "default",
26
+ "languages": [
27
+ "eng-Latn"
28
+ ]
29
+ }
30
+ ]
31
+ },
32
+ "evaluation_time": 7.578378677368164,
33
+ "kg_co2_emissions": null
34
+ }
results/StackExchangeClusteringP2P.v2.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "815ca46b2622cec33ccafc3735d572c266efdb44",
3
+ "task_name": "StackExchangeClusteringP2P.v2",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "v_measures": {
9
+ "Level 0": [
10
+ 0.409606,
11
+ 0.417217,
12
+ 0.420211,
13
+ 0.409225,
14
+ 0.413964,
15
+ 0.406734,
16
+ 0.419918,
17
+ 0.419058,
18
+ 0.415426,
19
+ 0.420281
20
+ ]
21
+ },
22
+ "v_measure": 0.415164,
23
+ "v_measure_std": 0.004821,
24
+ "main_score": 0.415164,
25
+ "hf_subset": "default",
26
+ "languages": [
27
+ "eng-Latn"
28
+ ]
29
+ }
30
+ ]
31
+ },
32
+ "evaluation_time": 43.319039821624756,
33
+ "kg_co2_emissions": null
34
+ }
results/SummEvalSummarization.v2.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "cda12ad7615edc362dbf25a00fdd61d3b1eaf93c",
3
+ "task_name": "SummEvalSummarization.v2",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "pearson": 0.372641,
9
+ "spearman": 0.318366,
10
+ "cosine_spearman": 0.318366,
11
+ "cosine_pearson": 0.372641,
12
+ "dot_pearson": 0.372641,
13
+ "dot_spearman": 0.318366,
14
+ "main_score": 0.318366,
15
+ "hf_subset": "default",
16
+ "languages": [
17
+ "eng-Latn"
18
+ ]
19
+ }
20
+ ]
21
+ },
22
+ "evaluation_time": 8.600267887115479,
23
+ "kg_co2_emissions": null
24
+ }
results/TRECCOVID.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "bb9466bac8153a0349341eb1b22e06409e78ef4e",
3
+ "task_name": "TRECCOVID",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "ndcg_at_1": 0.88,
9
+ "ndcg_at_3": 0.8152,
10
+ "ndcg_at_5": 0.80455,
11
+ "ndcg_at_10": 0.76872,
12
+ "ndcg_at_20": 0.73555,
13
+ "ndcg_at_100": 0.60746,
14
+ "ndcg_at_1000": 0.55158,
15
+ "map_at_1": 0.00245,
16
+ "map_at_3": 0.00648,
17
+ "map_at_5": 0.01024,
18
+ "map_at_10": 0.01871,
19
+ "map_at_20": 0.03405,
20
+ "map_at_100": 0.11928,
21
+ "map_at_1000": 0.29803,
22
+ "recall_at_1": 0.00245,
23
+ "recall_at_3": 0.00669,
24
+ "recall_at_5": 0.01095,
25
+ "recall_at_10": 0.02052,
26
+ "recall_at_20": 0.03915,
27
+ "recall_at_100": 0.15142,
28
+ "recall_at_1000": 0.52672,
29
+ "accuracy": 0.00245,
30
+ "precision_at_1": 0.92,
31
+ "precision_at_3": 0.86,
32
+ "precision_at_5": 0.844,
33
+ "precision_at_10": 0.804,
34
+ "precision_at_20": 0.768,
35
+ "precision_at_100": 0.6292,
36
+ "precision_at_1000": 0.24724,
37
+ "mrr_at_1": 0.92,
38
+ "mrr_at_3": 0.95,
39
+ "mrr_at_5": 0.955,
40
+ "mrr_at_10": 0.955,
41
+ "mrr_at_20": 0.955,
42
+ "mrr_at_100": 0.955,
43
+ "mrr_at_1000": 0.955,
44
+ "nauc_ndcg_at_1_max": -0.091055,
45
+ "nauc_ndcg_at_1_std": 0.217061,
46
+ "nauc_ndcg_at_1_diff1": -0.046573,
47
+ "nauc_ndcg_at_3_max": 0.315341,
48
+ "nauc_ndcg_at_3_std": 0.557583,
49
+ "nauc_ndcg_at_3_diff1": -0.221223,
50
+ "nauc_ndcg_at_5_max": 0.349174,
51
+ "nauc_ndcg_at_5_std": 0.608116,
52
+ "nauc_ndcg_at_5_diff1": -0.161243,
53
+ "nauc_ndcg_at_10_max": 0.37277,
54
+ "nauc_ndcg_at_10_std": 0.631019,
55
+ "nauc_ndcg_at_10_diff1": -0.129764,
56
+ "nauc_ndcg_at_20_max": 0.453586,
57
+ "nauc_ndcg_at_20_std": 0.736933,
58
+ "nauc_ndcg_at_20_diff1": -0.146207,
59
+ "nauc_ndcg_at_100_max": 0.530136,
60
+ "nauc_ndcg_at_100_std": 0.812709,
61
+ "nauc_ndcg_at_100_diff1": -0.232757,
62
+ "nauc_ndcg_at_1000_max": 0.57971,
63
+ "nauc_ndcg_at_1000_std": 0.816324,
64
+ "nauc_ndcg_at_1000_diff1": -0.086233,
65
+ "nauc_map_at_1_max": -0.050196,
66
+ "nauc_map_at_1_std": -0.114799,
67
+ "nauc_map_at_1_diff1": 0.311602,
68
+ "nauc_map_at_3_max": 0.065619,
69
+ "nauc_map_at_3_std": 0.06485,
70
+ "nauc_map_at_3_diff1": 0.266514,
71
+ "nauc_map_at_5_max": 0.097421,
72
+ "nauc_map_at_5_std": 0.13398,
73
+ "nauc_map_at_5_diff1": 0.223031,
74
+ "nauc_map_at_10_max": 0.135991,
75
+ "nauc_map_at_10_std": 0.199769,
76
+ "nauc_map_at_10_diff1": 0.187475,
77
+ "nauc_map_at_20_max": 0.195794,
78
+ "nauc_map_at_20_std": 0.313348,
79
+ "nauc_map_at_20_diff1": 0.161823,
80
+ "nauc_map_at_100_max": 0.414433,
81
+ "nauc_map_at_100_std": 0.655214,
82
+ "nauc_map_at_100_diff1": -0.020876,
83
+ "nauc_map_at_1000_max": 0.580533,
84
+ "nauc_map_at_1000_std": 0.826205,
85
+ "nauc_map_at_1000_diff1": -0.132091,
86
+ "nauc_recall_at_1_max": -0.050196,
87
+ "nauc_recall_at_1_std": -0.114799,
88
+ "nauc_recall_at_1_diff1": 0.311602,
89
+ "nauc_recall_at_3_max": 0.077899,
90
+ "nauc_recall_at_3_std": 0.065619,
91
+ "nauc_recall_at_3_diff1": 0.260918,
92
+ "nauc_recall_at_5_max": 0.05499,
93
+ "nauc_recall_at_5_std": 0.091834,
94
+ "nauc_recall_at_5_diff1": 0.228808,
95
+ "nauc_recall_at_10_max": 0.081645,
96
+ "nauc_recall_at_10_std": 0.133833,
97
+ "nauc_recall_at_10_diff1": 0.22023,
98
+ "nauc_recall_at_20_max": 0.123296,
99
+ "nauc_recall_at_20_std": 0.207722,
100
+ "nauc_recall_at_20_diff1": 0.204419,
101
+ "nauc_recall_at_100_max": 0.323222,
102
+ "nauc_recall_at_100_std": 0.508277,
103
+ "nauc_recall_at_100_diff1": 0.054763,
104
+ "nauc_recall_at_1000_max": 0.53146,
105
+ "nauc_recall_at_1000_std": 0.724977,
106
+ "nauc_recall_at_1000_diff1": -0.017566,
107
+ "nauc_precision_at_1_max": 0.022176,
108
+ "nauc_precision_at_1_std": 0.010387,
109
+ "nauc_precision_at_1_diff1": 0.496032,
110
+ "nauc_precision_at_3_max": 0.529013,
111
+ "nauc_precision_at_3_std": 0.634598,
112
+ "nauc_precision_at_3_diff1": 0.063245,
113
+ "nauc_precision_at_5_max": 0.445996,
114
+ "nauc_precision_at_5_std": 0.63887,
115
+ "nauc_precision_at_5_diff1": 0.031821,
116
+ "nauc_precision_at_10_max": 0.39863,
117
+ "nauc_precision_at_10_std": 0.596134,
118
+ "nauc_precision_at_10_diff1": 0.026692,
119
+ "nauc_precision_at_20_max": 0.511021,
120
+ "nauc_precision_at_20_std": 0.732895,
121
+ "nauc_precision_at_20_diff1": -0.039356,
122
+ "nauc_precision_at_100_max": 0.573319,
123
+ "nauc_precision_at_100_std": 0.817085,
124
+ "nauc_precision_at_100_diff1": -0.199203,
125
+ "nauc_precision_at_1000_max": 0.487604,
126
+ "nauc_precision_at_1000_std": 0.501679,
127
+ "nauc_precision_at_1000_diff1": -0.151466,
128
+ "nauc_mrr_at_1_max": 0.022176,
129
+ "nauc_mrr_at_1_std": 0.010387,
130
+ "nauc_mrr_at_1_diff1": 0.496032,
131
+ "nauc_mrr_at_3_max": 0.21774,
132
+ "nauc_mrr_at_3_std": 0.119141,
133
+ "nauc_mrr_at_3_diff1": 0.570682,
134
+ "nauc_mrr_at_5_max": 0.130823,
135
+ "nauc_mrr_at_5_std": 0.070806,
136
+ "nauc_mrr_at_5_diff1": 0.537504,
137
+ "nauc_mrr_at_10_max": 0.130823,
138
+ "nauc_mrr_at_10_std": 0.070806,
139
+ "nauc_mrr_at_10_diff1": 0.537504,
140
+ "nauc_mrr_at_20_max": 0.130823,
141
+ "nauc_mrr_at_20_std": 0.070806,
142
+ "nauc_mrr_at_20_diff1": 0.537504,
143
+ "nauc_mrr_at_100_max": 0.130823,
144
+ "nauc_mrr_at_100_std": 0.070806,
145
+ "nauc_mrr_at_100_diff1": 0.537504,
146
+ "nauc_mrr_at_1000_max": 0.130823,
147
+ "nauc_mrr_at_1000_std": 0.070806,
148
+ "nauc_mrr_at_1000_diff1": 0.537504,
149
+ "cv_recall_at_1": 0.92,
150
+ "cv_recall_at_3": 0.98,
151
+ "cv_recall_at_5": 1.0,
152
+ "cv_recall_at_10": 1.0,
153
+ "cv_recall_at_20": 1.0,
154
+ "cv_recall_at_100": 1.0,
155
+ "cv_recall_at_1000": 1.0,
156
+ "main_score": 0.76872,
157
+ "hf_subset": "default",
158
+ "languages": [
159
+ "eng-Latn"
160
+ ]
161
+ }
162
+ ]
163
+ },
164
+ "evaluation_time": 2064.53754734993,
165
+ "kg_co2_emissions": null
166
+ }
results/Touche2020Retrieval.v3.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "431886eaecc48f067a3975b70d0949ea2862463c",
3
+ "task_name": "Touche2020Retrieval.v3",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "ndcg_at_1": 0.73469,
9
+ "ndcg_at_3": 0.73816,
10
+ "ndcg_at_5": 0.69581,
11
+ "ndcg_at_10": 0.63082,
12
+ "ndcg_at_20": 0.55837,
13
+ "ndcg_at_100": 0.6173,
14
+ "ndcg_at_1000": 0.73006,
15
+ "map_at_1": 0.03145,
16
+ "map_at_3": 0.08598,
17
+ "map_at_5": 0.12629,
18
+ "map_at_10": 0.20962,
19
+ "map_at_20": 0.29337,
20
+ "map_at_100": 0.39787,
21
+ "map_at_1000": 0.429,
22
+ "recall_at_1": 0.03145,
23
+ "recall_at_3": 0.09023,
24
+ "recall_at_5": 0.13592,
25
+ "recall_at_10": 0.23882,
26
+ "recall_at_20": 0.36098,
27
+ "recall_at_100": 0.62422,
28
+ "recall_at_1000": 0.90653,
29
+ "accuracy": 0.03145,
30
+ "precision_at_1": 0.81633,
31
+ "precision_at_3": 0.82313,
32
+ "precision_at_5": 0.7551,
33
+ "precision_at_10": 0.66735,
34
+ "precision_at_20": 0.52041,
35
+ "precision_at_100": 0.19878,
36
+ "precision_at_1000": 0.03133,
37
+ "mrr_at_1": 0.816327,
38
+ "mrr_at_3": 0.891156,
39
+ "mrr_at_5": 0.891156,
40
+ "mrr_at_10": 0.893707,
41
+ "mrr_at_20": 0.893707,
42
+ "mrr_at_100": 0.893707,
43
+ "mrr_at_1000": 0.893707,
44
+ "nauc_ndcg_at_1_max": 0.017094,
45
+ "nauc_ndcg_at_1_std": 0.32688,
46
+ "nauc_ndcg_at_1_diff1": 0.385727,
47
+ "nauc_ndcg_at_3_max": 0.18549,
48
+ "nauc_ndcg_at_3_std": 0.338154,
49
+ "nauc_ndcg_at_3_diff1": 0.084536,
50
+ "nauc_ndcg_at_5_max": 0.249806,
51
+ "nauc_ndcg_at_5_std": 0.388384,
52
+ "nauc_ndcg_at_5_diff1": -0.025674,
53
+ "nauc_ndcg_at_10_max": 0.208167,
54
+ "nauc_ndcg_at_10_std": 0.407186,
55
+ "nauc_ndcg_at_10_diff1": -0.002949,
56
+ "nauc_ndcg_at_20_max": 0.124202,
57
+ "nauc_ndcg_at_20_std": 0.317238,
58
+ "nauc_ndcg_at_20_diff1": 0.116561,
59
+ "nauc_ndcg_at_100_max": -0.031738,
60
+ "nauc_ndcg_at_100_std": 0.330137,
61
+ "nauc_ndcg_at_100_diff1": 8.7e-05,
62
+ "nauc_ndcg_at_1000_max": 0.165674,
63
+ "nauc_ndcg_at_1000_std": 0.53676,
64
+ "nauc_ndcg_at_1000_diff1": -0.013159,
65
+ "nauc_map_at_1_max": -0.398856,
66
+ "nauc_map_at_1_std": -0.243935,
67
+ "nauc_map_at_1_diff1": 0.439361,
68
+ "nauc_map_at_3_max": -0.319297,
69
+ "nauc_map_at_3_std": -0.221661,
70
+ "nauc_map_at_3_diff1": 0.309201,
71
+ "nauc_map_at_5_max": -0.25699,
72
+ "nauc_map_at_5_std": -0.156081,
73
+ "nauc_map_at_5_diff1": 0.191318,
74
+ "nauc_map_at_10_max": -0.219695,
75
+ "nauc_map_at_10_std": -0.099567,
76
+ "nauc_map_at_10_diff1": 0.089682,
77
+ "nauc_map_at_20_max": -0.144479,
78
+ "nauc_map_at_20_std": -0.004943,
79
+ "nauc_map_at_20_diff1": 0.086786,
80
+ "nauc_map_at_100_max": -0.059458,
81
+ "nauc_map_at_100_std": 0.174008,
82
+ "nauc_map_at_100_diff1": -0.018566,
83
+ "nauc_map_at_1000_max": -0.017359,
84
+ "nauc_map_at_1000_std": 0.227759,
85
+ "nauc_map_at_1000_diff1": -0.032088,
86
+ "nauc_recall_at_1_max": -0.398856,
87
+ "nauc_recall_at_1_std": -0.243935,
88
+ "nauc_recall_at_1_diff1": 0.439361,
89
+ "nauc_recall_at_3_max": -0.326622,
90
+ "nauc_recall_at_3_std": -0.252416,
91
+ "nauc_recall_at_3_diff1": 0.277462,
92
+ "nauc_recall_at_5_max": -0.264213,
93
+ "nauc_recall_at_5_std": -0.178661,
94
+ "nauc_recall_at_5_diff1": 0.159087,
95
+ "nauc_recall_at_10_max": -0.230332,
96
+ "nauc_recall_at_10_std": -0.112774,
97
+ "nauc_recall_at_10_diff1": 0.074254,
98
+ "nauc_recall_at_20_max": -0.149974,
99
+ "nauc_recall_at_20_std": 0.008235,
100
+ "nauc_recall_at_20_diff1": 0.062604,
101
+ "nauc_recall_at_100_max": -0.071434,
102
+ "nauc_recall_at_100_std": 0.280979,
103
+ "nauc_recall_at_100_diff1": -0.154844,
104
+ "nauc_recall_at_1000_max": 0.258633,
105
+ "nauc_recall_at_1000_std": 0.707213,
106
+ "nauc_recall_at_1000_diff1": -0.201835,
107
+ "nauc_precision_at_1_max": -0.196217,
108
+ "nauc_precision_at_1_std": 0.189272,
109
+ "nauc_precision_at_1_diff1": 0.635523,
110
+ "nauc_precision_at_3_max": 0.053722,
111
+ "nauc_precision_at_3_std": 0.12829,
112
+ "nauc_precision_at_3_diff1": 0.093142,
113
+ "nauc_precision_at_5_max": 0.178316,
114
+ "nauc_precision_at_5_std": 0.232198,
115
+ "nauc_precision_at_5_diff1": -0.077635,
116
+ "nauc_precision_at_10_max": 0.150873,
117
+ "nauc_precision_at_10_std": 0.317674,
118
+ "nauc_precision_at_10_diff1": -0.171876,
119
+ "nauc_precision_at_20_max": 0.287779,
120
+ "nauc_precision_at_20_std": 0.523566,
121
+ "nauc_precision_at_20_diff1": -0.089179,
122
+ "nauc_precision_at_100_max": 0.424375,
123
+ "nauc_precision_at_100_std": 0.676656,
124
+ "nauc_precision_at_100_diff1": -0.328868,
125
+ "nauc_precision_at_1000_max": 0.466053,
126
+ "nauc_precision_at_1000_std": 0.385238,
127
+ "nauc_precision_at_1000_diff1": -0.217935,
128
+ "nauc_mrr_at_1_max": -0.196217,
129
+ "nauc_mrr_at_1_std": 0.189272,
130
+ "nauc_mrr_at_1_diff1": 0.635523,
131
+ "nauc_mrr_at_3_max": -0.203451,
132
+ "nauc_mrr_at_3_std": 0.076802,
133
+ "nauc_mrr_at_3_diff1": 0.524238,
134
+ "nauc_mrr_at_5_max": -0.203451,
135
+ "nauc_mrr_at_5_std": 0.076802,
136
+ "nauc_mrr_at_5_diff1": 0.524238,
137
+ "nauc_mrr_at_10_max": -0.204398,
138
+ "nauc_mrr_at_10_std": 0.107218,
139
+ "nauc_mrr_at_10_diff1": 0.551393,
140
+ "nauc_mrr_at_20_max": -0.204398,
141
+ "nauc_mrr_at_20_std": 0.107218,
142
+ "nauc_mrr_at_20_diff1": 0.551393,
143
+ "nauc_mrr_at_100_max": -0.204398,
144
+ "nauc_mrr_at_100_std": 0.107218,
145
+ "nauc_mrr_at_100_diff1": 0.551393,
146
+ "nauc_mrr_at_1000_max": -0.204398,
147
+ "nauc_mrr_at_1000_std": 0.107218,
148
+ "nauc_mrr_at_1000_diff1": 0.551393,
149
+ "cv_recall_at_1": 0.81633,
150
+ "cv_recall_at_3": 0.97959,
151
+ "cv_recall_at_5": 0.97959,
152
+ "cv_recall_at_10": 1.0,
153
+ "cv_recall_at_20": 1.0,
154
+ "cv_recall_at_100": 1.0,
155
+ "cv_recall_at_1000": 1.0,
156
+ "main_score": 0.63082,
157
+ "hf_subset": "default",
158
+ "languages": [
159
+ "eng-Latn"
160
+ ]
161
+ }
162
+ ]
163
+ },
164
+ "evaluation_time": 3874.1273472309113,
165
+ "kg_co2_emissions": null
166
+ }
results/ToxicConversationsClassification.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "edfaf9da55d3dd50d43143d90c1ac476895ae6de",
3
+ "task_name": "ToxicConversationsClassification",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "scores_per_experiment": [
9
+ {
10
+ "accuracy": 0.788574,
11
+ "f1": 0.591226,
12
+ "f1_weighted": 0.830318,
13
+ "precision": 0.582852,
14
+ "precision_weighted": 0.898953,
15
+ "recall": 0.699,
16
+ "recall_weighted": 0.788574,
17
+ "ap": 0.155097,
18
+ "ap_weighted": 0.155097
19
+ },
20
+ {
21
+ "accuracy": 0.739258,
22
+ "f1": 0.549093,
23
+ "f1_weighted": 0.795592,
24
+ "precision": 0.559275,
25
+ "precision_weighted": 0.890781,
26
+ "recall": 0.660939,
27
+ "recall_weighted": 0.739258,
28
+ "ap": 0.128149,
29
+ "ap_weighted": 0.128149
30
+ },
31
+ {
32
+ "accuracy": 0.837891,
33
+ "f1": 0.647019,
34
+ "f1_weighted": 0.86552,
35
+ "precision": 0.621072,
36
+ "precision_weighted": 0.911286,
37
+ "recall": 0.751168,
38
+ "recall_weighted": 0.837891,
39
+ "ap": 0.206926,
40
+ "ap_weighted": 0.206926
41
+ },
42
+ {
43
+ "accuracy": 0.784668,
44
+ "f1": 0.585844,
45
+ "f1_weighted": 0.827403,
46
+ "precision": 0.579137,
47
+ "precision_weighted": 0.897212,
48
+ "recall": 0.691237,
49
+ "recall_weighted": 0.784668,
50
+ "ap": 0.149998,
51
+ "ap_weighted": 0.149998
52
+ },
53
+ {
54
+ "accuracy": 0.638184,
55
+ "f1": 0.502688,
56
+ "f1_weighted": 0.721205,
57
+ "precision": 0.555362,
58
+ "precision_weighted": 0.900252,
59
+ "recall": 0.682236,
60
+ "recall_weighted": 0.638184,
61
+ "ap": 0.127989,
62
+ "ap_weighted": 0.127989
63
+ },
64
+ {
65
+ "accuracy": 0.553223,
66
+ "f1": 0.448916,
67
+ "f1_weighted": 0.65074,
68
+ "precision": 0.541336,
69
+ "precision_weighted": 0.894661,
70
+ "recall": 0.641749,
71
+ "recall_weighted": 0.553223,
72
+ "ap": 0.11085,
73
+ "ap_weighted": 0.11085
74
+ },
75
+ {
76
+ "accuracy": 0.714844,
77
+ "f1": 0.533916,
78
+ "f1_weighted": 0.778367,
79
+ "precision": 0.553405,
80
+ "precision_weighted": 0.889541,
81
+ "recall": 0.653326,
82
+ "recall_weighted": 0.714844,
83
+ "ap": 0.122618,
84
+ "ap_weighted": 0.122618
85
+ },
86
+ {
87
+ "accuracy": 0.67041,
88
+ "f1": 0.522062,
89
+ "f1_weighted": 0.74621,
90
+ "precision": 0.560201,
91
+ "precision_weighted": 0.900704,
92
+ "recall": 0.69127,
93
+ "recall_weighted": 0.67041,
94
+ "ap": 0.133953,
95
+ "ap_weighted": 0.133953
96
+ },
97
+ {
98
+ "accuracy": 0.702148,
99
+ "f1": 0.536639,
100
+ "f1_weighted": 0.769758,
101
+ "precision": 0.560974,
102
+ "precision_weighted": 0.89714,
103
+ "recall": 0.68311,
104
+ "recall_weighted": 0.702148,
105
+ "ap": 0.133612,
106
+ "ap_weighted": 0.133612
107
+ },
108
+ {
109
+ "accuracy": 0.745605,
110
+ "f1": 0.566224,
111
+ "f1_weighted": 0.801041,
112
+ "precision": 0.572997,
113
+ "precision_weighted": 0.900004,
114
+ "recall": 0.701062,
115
+ "recall_weighted": 0.745605,
116
+ "ap": 0.147438,
117
+ "ap_weighted": 0.147438
118
+ }
119
+ ],
120
+ "accuracy": 0.71748,
121
+ "f1": 0.548363,
122
+ "f1_weighted": 0.778615,
123
+ "precision": 0.568661,
124
+ "precision_weighted": 0.898054,
125
+ "recall": 0.68551,
126
+ "recall_weighted": 0.71748,
127
+ "ap": 0.141663,
128
+ "ap_weighted": 0.141663,
129
+ "main_score": 0.71748,
130
+ "hf_subset": "default",
131
+ "languages": [
132
+ "eng-Latn"
133
+ ]
134
+ }
135
+ ]
136
+ },
137
+ "evaluation_time": 40.886521339416504,
138
+ "kg_co2_emissions": null
139
+ }
results/TweetSentimentExtractionClassification.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "d604517c81ca91fe16a244d1248fc021f9ecee7a",
3
+ "task_name": "TweetSentimentExtractionClassification",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "scores_per_experiment": [
9
+ {
10
+ "accuracy": 0.60017,
11
+ "f1": 0.602466,
12
+ "f1_weighted": 0.593331,
13
+ "precision": 0.599598,
14
+ "precision_weighted": 0.598729,
15
+ "recall": 0.616661,
16
+ "recall_weighted": 0.60017,
17
+ "ap": null,
18
+ "ap_weighted": null
19
+ },
20
+ {
21
+ "accuracy": 0.589983,
22
+ "f1": 0.592724,
23
+ "f1_weighted": 0.582562,
24
+ "precision": 0.589319,
25
+ "precision_weighted": 0.588772,
26
+ "recall": 0.608987,
27
+ "recall_weighted": 0.589983,
28
+ "ap": null,
29
+ "ap_weighted": null
30
+ },
31
+ {
32
+ "accuracy": 0.608659,
33
+ "f1": 0.610167,
34
+ "f1_weighted": 0.601373,
35
+ "precision": 0.612042,
36
+ "precision_weighted": 0.615692,
37
+ "recall": 0.628804,
38
+ "recall_weighted": 0.608659,
39
+ "ap": null,
40
+ "ap_weighted": null
41
+ },
42
+ {
43
+ "accuracy": 0.588851,
44
+ "f1": 0.591059,
45
+ "f1_weighted": 0.579425,
46
+ "precision": 0.591457,
47
+ "precision_weighted": 0.591131,
48
+ "recall": 0.611816,
49
+ "recall_weighted": 0.588851,
50
+ "ap": null,
51
+ "ap_weighted": null
52
+ },
53
+ {
54
+ "accuracy": 0.60781,
55
+ "f1": 0.611659,
56
+ "f1_weighted": 0.603352,
57
+ "precision": 0.609397,
58
+ "precision_weighted": 0.609397,
59
+ "recall": 0.62428,
60
+ "recall_weighted": 0.60781,
61
+ "ap": null,
62
+ "ap_weighted": null
63
+ },
64
+ {
65
+ "accuracy": 0.605546,
66
+ "f1": 0.609391,
67
+ "f1_weighted": 0.598667,
68
+ "precision": 0.606539,
69
+ "precision_weighted": 0.605213,
70
+ "recall": 0.625473,
71
+ "recall_weighted": 0.605546,
72
+ "ap": null,
73
+ "ap_weighted": null
74
+ },
75
+ {
76
+ "accuracy": 0.578664,
77
+ "f1": 0.577106,
78
+ "f1_weighted": 0.565601,
79
+ "precision": 0.576182,
80
+ "precision_weighted": 0.574397,
81
+ "recall": 0.598411,
82
+ "recall_weighted": 0.578664,
83
+ "ap": null,
84
+ "ap_weighted": null
85
+ },
86
+ {
87
+ "accuracy": 0.621109,
88
+ "f1": 0.624325,
89
+ "f1_weighted": 0.615278,
90
+ "precision": 0.620682,
91
+ "precision_weighted": 0.620097,
92
+ "recall": 0.637876,
93
+ "recall_weighted": 0.621109,
94
+ "ap": null,
95
+ "ap_weighted": null
96
+ },
97
+ {
98
+ "accuracy": 0.54584,
99
+ "f1": 0.548347,
100
+ "f1_weighted": 0.537797,
101
+ "precision": 0.544945,
102
+ "precision_weighted": 0.543678,
103
+ "recall": 0.564986,
104
+ "recall_weighted": 0.54584,
105
+ "ap": null,
106
+ "ap_weighted": null
107
+ },
108
+ {
109
+ "accuracy": 0.568478,
110
+ "f1": 0.574254,
111
+ "f1_weighted": 0.566821,
112
+ "precision": 0.571524,
113
+ "precision_weighted": 0.56722,
114
+ "recall": 0.579174,
115
+ "recall_weighted": 0.568478,
116
+ "ap": null,
117
+ "ap_weighted": null
118
+ }
119
+ ],
120
+ "accuracy": 0.591511,
121
+ "f1": 0.59415,
122
+ "f1_weighted": 0.584421,
123
+ "precision": 0.592169,
124
+ "precision_weighted": 0.591432,
125
+ "recall": 0.609647,
126
+ "recall_weighted": 0.591511,
127
+ "ap": NaN,
128
+ "ap_weighted": NaN,
129
+ "main_score": 0.591511,
130
+ "hf_subset": "default",
131
+ "languages": [
132
+ "eng-Latn"
133
+ ]
134
+ }
135
+ ]
136
+ },
137
+ "evaluation_time": 27.70308542251587,
138
+ "kg_co2_emissions": null
139
+ }
results/TwentyNewsgroupsClustering.v2.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "6125ec4e24fa026cec8a478383ee943acfbd5449",
3
+ "task_name": "TwentyNewsgroupsClustering.v2",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "v_measures": {
9
+ "Level 0": [
10
+ 0.499487,
11
+ 0.480407,
12
+ 0.504414,
13
+ 0.489002,
14
+ 0.508654,
15
+ 0.469198,
16
+ 0.490777,
17
+ 0.499505,
18
+ 0.508692,
19
+ 0.497074
20
+ ]
21
+ },
22
+ "v_measure": 0.494721,
23
+ "v_measure_std": 0.011996,
24
+ "main_score": 0.494721,
25
+ "hf_subset": "default",
26
+ "languages": [
27
+ "eng-Latn"
28
+ ]
29
+ }
30
+ ]
31
+ },
32
+ "evaluation_time": 3.2848246097564697,
33
+ "kg_co2_emissions": null
34
+ }
results/TwitterSemEval2015.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "70970daeab8776df92f5ea462b6173c0b46fd2d1",
3
+ "task_name": "TwitterSemEval2015",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "similarity_accuracy": 0.836979,
9
+ "similarity_f1": 0.620426,
10
+ "similarity_precision": 0.567367,
11
+ "similarity_recall": 0.684433,
12
+ "similarity_ap": 0.662835,
13
+ "cosine_accuracy": 0.836979,
14
+ "cosine_f1": 0.620426,
15
+ "cosine_precision": 0.567367,
16
+ "cosine_recall": 0.684433,
17
+ "cosine_ap": 0.662835,
18
+ "manhattan_accuracy": 0.836681,
19
+ "manhattan_f1": 0.62115,
20
+ "manhattan_precision": 0.574731,
21
+ "manhattan_recall": 0.675726,
22
+ "manhattan_ap": 0.662615,
23
+ "euclidean_accuracy": 0.836979,
24
+ "euclidean_f1": 0.620426,
25
+ "euclidean_precision": 0.567367,
26
+ "euclidean_recall": 0.684433,
27
+ "euclidean_ap": 0.662835,
28
+ "dot_accuracy": 0.836979,
29
+ "dot_f1": 0.620426,
30
+ "dot_precision": 0.567367,
31
+ "dot_recall": 0.684433,
32
+ "dot_ap": 0.662835,
33
+ "max_accuracy": 0.836979,
34
+ "max_f1": 0.62115,
35
+ "max_precision": 0.574731,
36
+ "max_recall": 0.684433,
37
+ "max_ap": 0.662835,
38
+ "main_score": 0.662835,
39
+ "hf_subset": "default",
40
+ "languages": [
41
+ "eng-Latn"
42
+ ]
43
+ }
44
+ ]
45
+ },
46
+ "evaluation_time": 22.922184705734253,
47
+ "kg_co2_emissions": null
48
+ }
results/TwitterURLCorpus.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_revision": "8b6510b0b1fa4e4c4f879467980e9be563ec1cdf",
3
+ "task_name": "TwitterURLCorpus",
4
+ "mteb_version": "2.3.5",
5
+ "scores": {
6
+ "test": [
7
+ {
8
+ "similarity_accuracy": 0.884115,
9
+ "similarity_f1": 0.768936,
10
+ "similarity_precision": 0.750531,
11
+ "similarity_recall": 0.788266,
12
+ "similarity_ap": 0.849454,
13
+ "cosine_accuracy": 0.884115,
14
+ "cosine_f1": 0.768936,
15
+ "cosine_precision": 0.750531,
16
+ "cosine_recall": 0.788266,
17
+ "cosine_ap": 0.849454,
18
+ "manhattan_accuracy": 0.884096,
19
+ "manhattan_f1": 0.770008,
20
+ "manhattan_precision": 0.754695,
21
+ "manhattan_recall": 0.785956,
22
+ "manhattan_ap": 0.849331,
23
+ "euclidean_accuracy": 0.884115,
24
+ "euclidean_f1": 0.768936,
25
+ "euclidean_precision": 0.750531,
26
+ "euclidean_recall": 0.788266,
27
+ "euclidean_ap": 0.849454,
28
+ "dot_accuracy": 0.884115,
29
+ "dot_f1": 0.768936,
30
+ "dot_precision": 0.750531,
31
+ "dot_recall": 0.788266,
32
+ "dot_ap": 0.849454,
33
+ "max_accuracy": 0.884115,
34
+ "max_f1": 0.770008,
35
+ "max_precision": 0.754695,
36
+ "max_recall": 0.788266,
37
+ "max_ap": 0.849454,
38
+ "main_score": 0.849454,
39
+ "hf_subset": "default",
40
+ "languages": [
41
+ "eng-Latn"
42
+ ]
43
+ }
44
+ ]
45
+ },
46
+ "evaluation_time": 108.92075967788696,
47
+ "kg_co2_emissions": null
48
+ }
results/model_meta.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"loader_kwargs": {}, "name": "electroglyph/test", "revision": "cf3639f629e99dec53cce217490b04c926b01ab7", "release_date": null, "languages": null, "n_parameters": null, "memory_usage_mb": null, "max_tokens": null, "embed_dim": null, "license": null, "open_weights": true, "public_training_code": null, "public_training_data": null, "framework": ["PyTorch"], "reference": null, "similarity_fn_name": null, "use_instructions": null, "training_datasets": null, "adapted_from": null, "superseded_by": null, "modalities": ["text"], "is_cross_encoder": null, "citation": null, "contacts": null, "loader": "sentence_transformers_loader"}