Skip to content

Commit

Permalink
add descriptive stats
Browse files Browse the repository at this point in the history
  • Loading branch information
Samoed committed Feb 5, 2025
1 parent 995f8ce commit ce8f057
Show file tree
Hide file tree
Showing 30 changed files with 2,153 additions and 1,492 deletions.
2,736 changes: 1,369 additions & 1,367 deletions mteb/benchmarks/benchmarks.py

Large diffs are not rendered by default.

31 changes: 31 additions & 0 deletions mteb/descriptive_stats/Retrieval/ArguAna-NL.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
{
"test": {
"num_samples": 10080,
"number_of_characters": 11742019,
"num_documents": 8674,
"min_document_length": 1,
"average_document_length": 1141.0074936592114,
"max_document_length": 7337,
"unique_documents": 8674,
"num_queries": 1406,
"min_query_length": 252,
"average_query_length": 1312.176386913229,
"max_query_length": 6050,
"unique_queries": 1406,
"none_queries": 0,
"num_relevant_docs": 1406,
"min_relevant_docs_per_query": 1,
"average_relevant_docs_per_query": 1.0,
"max_relevant_docs_per_query": 1,
"unique_relevant_docs": 1406,
"num_instructions": null,
"min_instruction_length": null,
"average_instruction_length": null,
"max_instruction_length": null,
"unique_instructions": null,
"num_top_ranked": null,
"min_top_ranked_per_query": null,
"average_top_ranked_per_query": null,
"max_top_ranked_per_query": null
}
}
31 changes: 31 additions & 0 deletions mteb/descriptive_stats/Retrieval/CQADupstackAndroid-NL.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
{
"test": {
"num_samples": 23697,
"number_of_characters": 15040973,
"num_documents": 22998,
"min_document_length": 61,
"average_document_length": 652.2017131924515,
"max_document_length": 7632,
"unique_documents": 22998,
"num_queries": 699,
"min_query_length": 16,
"average_query_length": 59.56795422031473,
"max_query_length": 162,
"unique_queries": 699,
"none_queries": 0,
"num_relevant_docs": 699,
"min_relevant_docs_per_query": 1,
"average_relevant_docs_per_query": 1.0,
"max_relevant_docs_per_query": 1,
"unique_relevant_docs": 699,
"num_instructions": null,
"min_instruction_length": null,
"average_instruction_length": null,
"max_instruction_length": null,
"unique_instructions": null,
"num_top_ranked": null,
"min_top_ranked_per_query": null,
"average_top_ranked_per_query": null,
"max_top_ranked_per_query": null
}
}
31 changes: 31 additions & 0 deletions mteb/descriptive_stats/Retrieval/CQADupstackEnglish-NL.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
{
"test": {
"num_samples": 41791,
"number_of_characters": 21159972,
"num_documents": 40221,
"min_document_length": 39,
"average_document_length": 524.0218293926058,
"max_document_length": 7083,
"unique_documents": 40221,
"num_queries": 1570,
"min_query_length": 8,
"average_query_length": 53.05095541401274,
"max_query_length": 179,
"unique_queries": 1570,
"none_queries": 0,
"num_relevant_docs": 1570,
"min_relevant_docs_per_query": 1,
"average_relevant_docs_per_query": 1.0,
"max_relevant_docs_per_query": 1,
"unique_relevant_docs": 1570,
"num_instructions": null,
"min_instruction_length": null,
"average_instruction_length": null,
"max_instruction_length": null,
"unique_instructions": null,
"num_top_ranked": null,
"min_top_ranked_per_query": null,
"average_top_ranked_per_query": null,
"max_top_ranked_per_query": null
}
}
31 changes: 31 additions & 0 deletions mteb/descriptive_stats/Retrieval/CQADupstackGaming-NL.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
{
"test": {
"num_samples": 46896,
"number_of_characters": 23837370,
"num_documents": 45301,
"min_document_length": 43,
"average_document_length": 524.2849385223284,
"max_document_length": 7875,
"unique_documents": 45301,
"num_queries": 1595,
"min_query_length": 13,
"average_query_length": 54.381191222570536,
"max_query_length": 162,
"unique_queries": 1595,
"none_queries": 0,
"num_relevant_docs": 1595,
"min_relevant_docs_per_query": 1,
"average_relevant_docs_per_query": 1.0,
"max_relevant_docs_per_query": 1,
"unique_relevant_docs": 1595,
"num_instructions": null,
"min_instruction_length": null,
"average_instruction_length": null,
"max_instruction_length": null,
"unique_instructions": null,
"num_top_ranked": null,
"min_top_ranked_per_query": null,
"average_top_ranked_per_query": null,
"max_top_ranked_per_query": null
}
}
31 changes: 31 additions & 0 deletions mteb/descriptive_stats/Retrieval/CQADupstackGis-NL.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
{
"test": {
"num_samples": 38522,
"number_of_characters": 39342944,
"num_documents": 37637,
"min_document_length": 55,
"average_document_length": 1043.934399659909,
"max_document_length": 12166,
"unique_documents": 37637,
"num_queries": 885,
"min_query_length": 14,
"average_query_length": 59.19209039548023,
"max_query_length": 166,
"unique_queries": 885,
"none_queries": 0,
"num_relevant_docs": 885,
"min_relevant_docs_per_query": 1,
"average_relevant_docs_per_query": 1.0,
"max_relevant_docs_per_query": 1,
"unique_relevant_docs": 885,
"num_instructions": null,
"min_instruction_length": null,
"average_instruction_length": null,
"max_instruction_length": null,
"unique_instructions": null,
"num_top_ranked": null,
"min_top_ranked_per_query": null,
"average_top_ranked_per_query": null,
"max_top_ranked_per_query": null
}
}
31 changes: 31 additions & 0 deletions mteb/descriptive_stats/Retrieval/CQADupstackMathematica-NL.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
{
"test": {
"num_samples": 17509,
"number_of_characters": 19566432,
"num_documents": 16705,
"min_document_length": 80,
"average_document_length": 1168.5997006884165,
"max_document_length": 8096,
"unique_documents": 16705,
"num_queries": 804,
"min_query_length": 12,
"average_query_length": 55.93781094527363,
"max_query_length": 155,
"unique_queries": 804,
"none_queries": 0,
"num_relevant_docs": 804,
"min_relevant_docs_per_query": 1,
"average_relevant_docs_per_query": 1.0,
"max_relevant_docs_per_query": 1,
"unique_relevant_docs": 804,
"num_instructions": null,
"min_instruction_length": null,
"average_instruction_length": null,
"max_instruction_length": null,
"unique_instructions": null,
"num_top_ranked": null,
"min_top_ranked_per_query": null,
"average_top_ranked_per_query": null,
"max_top_ranked_per_query": null
}
}
31 changes: 31 additions & 0 deletions mteb/descriptive_stats/Retrieval/CQADupstackPhysics-NL.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
{
"test": {
"num_samples": 39355,
"number_of_characters": 33903094,
"num_documents": 38316,
"min_document_length": 48,
"average_document_length": 883.2297734627832,
"max_document_length": 8858,
"unique_documents": 38316,
"num_queries": 1039,
"min_query_length": 12,
"average_query_length": 58.962463907603464,
"max_query_length": 167,
"unique_queries": 1039,
"none_queries": 0,
"num_relevant_docs": 1039,
"min_relevant_docs_per_query": 1,
"average_relevant_docs_per_query": 1.0,
"max_relevant_docs_per_query": 1,
"unique_relevant_docs": 1039,
"num_instructions": null,
"min_instruction_length": null,
"average_instruction_length": null,
"max_instruction_length": null,
"unique_instructions": null,
"num_top_ranked": null,
"min_top_ranked_per_query": null,
"average_top_ranked_per_query": null,
"max_top_ranked_per_query": null
}
}
31 changes: 31 additions & 0 deletions mteb/descriptive_stats/Retrieval/CQADupstackProgrammers-NL.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
{
"test": {
"num_samples": 33052,
"number_of_characters": 36939947,
"num_documents": 32176,
"min_document_length": 43,
"average_document_length": 1146.3740054699156,
"max_document_length": 10679,
"unique_documents": 32176,
"num_queries": 876,
"min_query_length": 13,
"average_query_length": 61.891552511415526,
"max_query_length": 205,
"unique_queries": 876,
"none_queries": 0,
"num_relevant_docs": 876,
"min_relevant_docs_per_query": 1,
"average_relevant_docs_per_query": 1.0,
"max_relevant_docs_per_query": 1,
"unique_relevant_docs": 876,
"num_instructions": null,
"min_instruction_length": null,
"average_instruction_length": null,
"max_instruction_length": null,
"unique_instructions": null,
"num_top_ranked": null,
"min_top_ranked_per_query": null,
"average_top_ranked_per_query": null,
"max_top_ranked_per_query": null
}
}
31 changes: 31 additions & 0 deletions mteb/descriptive_stats/Retrieval/CQADupstackStats-NL.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
{
"test": {
"num_samples": 42921,
"number_of_characters": 46869062,
"num_documents": 42269,
"min_document_length": 59,
"average_document_length": 1107.8497717003004,
"max_document_length": 9689,
"unique_documents": 42269,
"num_queries": 652,
"min_query_length": 15,
"average_query_length": 63.43558282208589,
"max_query_length": 173,
"unique_queries": 652,
"none_queries": 0,
"num_relevant_docs": 652,
"min_relevant_docs_per_query": 1,
"average_relevant_docs_per_query": 1.0,
"max_relevant_docs_per_query": 1,
"unique_relevant_docs": 652,
"num_instructions": null,
"min_instruction_length": null,
"average_instruction_length": null,
"max_instruction_length": null,
"unique_instructions": null,
"num_top_ranked": null,
"min_top_ranked_per_query": null,
"average_top_ranked_per_query": null,
"max_top_ranked_per_query": null
}
}
31 changes: 31 additions & 0 deletions mteb/descriptive_stats/Retrieval/CQADupstackTex-NL.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
{
"test": {
"num_samples": 71090,
"number_of_characters": 87941996,
"num_documents": 68184,
"min_document_length": 51,
"average_document_length": 1287.5021705972076,
"max_document_length": 13390,
"unique_documents": 68184,
"num_queries": 2906,
"min_query_length": 9,
"average_query_length": 53.32002752924983,
"max_query_length": 164,
"unique_queries": 2906,
"none_queries": 0,
"num_relevant_docs": 2906,
"min_relevant_docs_per_query": 1,
"average_relevant_docs_per_query": 1.0,
"max_relevant_docs_per_query": 1,
"unique_relevant_docs": 2906,
"num_instructions": null,
"min_instruction_length": null,
"average_instruction_length": null,
"max_instruction_length": null,
"unique_instructions": null,
"num_top_ranked": null,
"min_top_ranked_per_query": null,
"average_top_ranked_per_query": null,
"max_top_ranked_per_query": null
}
}
31 changes: 31 additions & 0 deletions mteb/descriptive_stats/Retrieval/CQADupstackUnix-NL.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
{
"test": {
"num_samples": 48454,
"number_of_characters": 47254187,
"num_documents": 47382,
"min_document_length": 54,
"average_document_length": 995.9870414925499,
"max_document_length": 15394,
"unique_documents": 47382,
"num_queries": 1072,
"min_query_length": 12,
"average_query_length": 58.14272388059702,
"max_query_length": 172,
"unique_queries": 1072,
"none_queries": 0,
"num_relevant_docs": 1072,
"min_relevant_docs_per_query": 1,
"average_relevant_docs_per_query": 1.0,
"max_relevant_docs_per_query": 1,
"unique_relevant_docs": 1072,
"num_instructions": null,
"min_instruction_length": null,
"average_instruction_length": null,
"max_instruction_length": null,
"unique_instructions": null,
"num_top_ranked": null,
"min_top_ranked_per_query": null,
"average_top_ranked_per_query": null,
"max_top_ranked_per_query": null
}
}
31 changes: 31 additions & 0 deletions mteb/descriptive_stats/Retrieval/CQADupstackWebmasters-NL.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
{
"test": {
"num_samples": 17911,
"number_of_characters": 13318993,
"num_documents": 17405,
"min_document_length": 47,
"average_document_length": 763.5184142487791,
"max_document_length": 8733,
"unique_documents": 17405,
"num_queries": 506,
"min_query_length": 13,
"average_query_length": 59.19960474308301,
"max_query_length": 153,
"unique_queries": 506,
"none_queries": 0,
"num_relevant_docs": 506,
"min_relevant_docs_per_query": 1,
"average_relevant_docs_per_query": 1.0,
"max_relevant_docs_per_query": 1,
"unique_relevant_docs": 506,
"num_instructions": null,
"min_instruction_length": null,
"average_instruction_length": null,
"max_instruction_length": null,
"unique_instructions": null,
"num_top_ranked": null,
"min_top_ranked_per_query": null,
"average_top_ranked_per_query": null,
"max_top_ranked_per_query": null
}
}
Loading

0 comments on commit ce8f057

Please sign in to comment.