Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
125 commits
Select commit Hold shift + click to select a range
f54cb2d
feat: add KaLM-Team/KaLM_Embedding_X_0605
Jun 5, 2025
b05f28e
feat: add KaLM-Team/KaLM_Embedding_X_0605
Jun 5, 2025
4086595
feat: add KaLM-Team/KaLM-Embedding-X-0605
Jun 5, 2025
cd2abb9
Add files via upload
ll0ruc May 29, 2025
2b3c9b2
Add files via upload
ll0ruc May 29, 2025
8ccd077
Add files via upload
ll0ruc May 29, 2025
4b525e1
Add files via upload
ll0ruc May 29, 2025
8b5588f
Add files via upload
ll0ruc May 29, 2025
c630143
Add files via upload
ll0ruc May 29, 2025
b7da47c
Add files via upload
ll0ruc May 29, 2025
bff6c96
Add files via upload
ll0ruc May 29, 2025
d7b5fec
Add files via upload
ll0ruc May 29, 2025
179adf8
Add files via upload
ll0ruc May 29, 2025
d41d179
Add files via upload
ll0ruc May 29, 2025
ad687ca
Add files via upload
ll0ruc May 29, 2025
0f49e40
Add files via upload
ll0ruc May 29, 2025
26b1ff3
Add files via upload
ll0ruc May 29, 2025
3dcdc7e
Add files via upload
ll0ruc May 29, 2025
527adf8
Add files via upload
ll0ruc May 29, 2025
133a423
Add files via upload
ll0ruc May 29, 2025
7995a25
Add files via upload
ll0ruc May 30, 2025
6fa55f7
Add files via upload
ll0ruc May 30, 2025
568670d
Add files via upload
ll0ruc May 30, 2025
44654a9
Add files via upload
ll0ruc May 30, 2025
c9c0b56
Update R2MEDRetrieval.json
ll0ruc Jun 3, 2025
5696821
Update R2MEDRetrieval.json
ll0ruc Jun 3, 2025
d884fe9
Update R2MEDRetrieval.json
ll0ruc Jun 3, 2025
5107605
Update R2MEDRetrieval.json
ll0ruc Jun 3, 2025
e5f725a
Update R2MEDRetrieval.json
ll0ruc Jun 3, 2025
026eaef
Update R2MEDRetrieval.json
ll0ruc Jun 3, 2025
7214377
Update R2MEDRetrieval.json
ll0ruc Jun 3, 2025
77898f7
Update R2MEDRetrieval.json
ll0ruc Jun 3, 2025
456c0c0
Update R2MEDRetrieval.json
ll0ruc Jun 3, 2025
4907772
Update R2MEDRetrieval.json
ll0ruc Jun 3, 2025
3aacdb7
Update R2MEDRetrieval.json
ll0ruc Jun 3, 2025
cbb302e
Update R2MEDRetrieval.json
ll0ruc Jun 3, 2025
8e99fb8
Update R2MEDRetrieval.json
ll0ruc Jun 3, 2025
454917d
Update R2MEDRetrieval.json
ll0ruc Jun 3, 2025
6995340
Update R2MEDRetrieval.json
ll0ruc Jun 3, 2025
221ef89
Update R2MEDRetrieval.json
ll0ruc Jun 3, 2025
2efa7be
Update R2MEDRetrieval.json
ll0ruc Jun 3, 2025
119dd9e
Update R2MEDRetrieval.json
ll0ruc Jun 3, 2025
5924834
Update R2MEDRetrieval.json
ll0ruc Jun 3, 2025
e26774b
Update R2MEDRetrieval.json
ll0ruc Jun 3, 2025
f2dfcbb
Delete results/yibinlei__LENS-d4000/external/R2MEDRetrieval.json
ll0ruc Jun 5, 2025
10fd883
Delete results/yibinlei__LENS-d8000/external/R2MEDRetrieval.json
ll0ruc Jun 5, 2025
6b5cc18
Add files via upload
ll0ruc Jun 5, 2025
aaeee90
Add files via upload
ll0ruc Jun 5, 2025
5da111a
Add files via upload
ll0ruc Jun 5, 2025
1df40f6
Delete results/Alibaba-NLP__gte-Qwen2-1.5B-instruct/c6c1b92f4a3e1b92b…
ll0ruc Jun 5, 2025
31a9143
Add files via upload
ll0ruc Jun 5, 2025
f9a1ea3
Delete results/Alibaba-NLP__gte-Qwen2-7B-instruct/e26182b2122f4435e8b…
ll0ruc Jun 5, 2025
0a902c7
Add files via upload
ll0ruc Jun 5, 2025
7af000c
Delete results/BAAI__bge-large-en-v1.5/d4aa6901d3a41ba39fb536a557fa16…
ll0ruc Jun 5, 2025
585f7ac
Add files via upload
ll0ruc Jun 5, 2025
eafa116
Delete results/BAAI__bge-m3/5617a9f61b028005a4858fdac845db406aefb181/…
ll0ruc Jun 5, 2025
af325bf
Add files via upload
ll0ruc Jun 5, 2025
37dac9f
Delete results/BAAI__bge-small-en-v1.5/5c38ec7c405ec4b44b94cc5a9bb96e…
ll0ruc Jun 5, 2025
607aae2
Add files via upload
ll0ruc Jun 5, 2025
bba7949
Delete results/GritLM__GritLM-7B/13f00a0e36500c80ce12870ea513846a0660…
ll0ruc Jun 5, 2025
2d18173
Add files via upload
ll0ruc Jun 5, 2025
ecc6206
Delete results/infly__inf-retriever-v1/cb70ca7c31dfa866b2eff2dad229c1…
ll0ruc Jun 5, 2025
a324760
Add files via upload
ll0ruc Jun 5, 2025
fa53e7f
Delete results/infly__inf-retriever-v1-1.5b/c9c05c2dd50707a486966ba81…
ll0ruc Jun 5, 2025
d29a3b7
Add files via upload
ll0ruc Jun 5, 2025
ddd0a39
Delete results/intfloat__e5-mistral-7b-instruct/07163b72af1488142a360…
ll0ruc Jun 5, 2025
ed9f610
Add files via upload
ll0ruc Jun 5, 2025
3e28afa
Delete results/intfloat__multilingual-e5-base/d13f1b27baf31030b7fd040…
ll0ruc Jun 5, 2025
9da0b7b
Delete results/intfloat__multilingual-e5-large/ab10c1a7f42e74530fe7ae…
ll0ruc Jun 5, 2025
08e8248
Delete results/intfloat__multilingual-e5-small/fd1525a9fd15316a2d503b…
ll0ruc Jun 5, 2025
243a7f3
Add files via upload
ll0ruc Jun 5, 2025
01daf95
Add files via upload
ll0ruc Jun 5, 2025
9bee69d
Add files via upload
ll0ruc Jun 5, 2025
e6da2a4
Delete results/NovaSearch__stella_en_400M_v5/1bb50bc7bb726810eac2140e…
ll0ruc Jun 5, 2025
ea1a913
Delete results/NovaSearch__stella_en_1.5B_v5/d03be74b361d4eb24f42a2fe…
ll0ruc Jun 5, 2025
cefe475
Add files via upload
ll0ruc Jun 5, 2025
2d707bc
Add files via upload
ll0ruc Jun 5, 2025
433e53d
Delete results/Salesforce__SFR-Embedding-2_R/91762139d94ed4371a9fa31d…
ll0ruc Jun 5, 2025
0f4678c
Delete results/Salesforce__SFR-Embedding-Mistral/938c560d1c236aa563b2…
ll0ruc Jun 5, 2025
a145e16
Add files via upload
ll0ruc Jun 5, 2025
5d63dcf
Add files via upload
ll0ruc Jun 5, 2025
a823ba3
Delete results/sentence-transformers__all-mpnet-base-v2/9a3225965996d…
ll0ruc Jun 5, 2025
81147f2
Delete results/sentence-transformers__paraphrase-multilingual-MiniLM-…
ll0ruc Jun 5, 2025
222ef2f
Add files via upload
ll0ruc Jun 5, 2025
444a9f8
Add files via upload
ll0ruc Jun 5, 2025
3bba32c
Delete results/yibinlei__LENS-d4000/e473b33364e6c48a324796fd1411d3b93…
ll0ruc Jun 5, 2025
883d0cf
Delete results/yibinlei__LENS-d8000/a0b87bd91cb27b6f2f0b0fe22c28026da…
ll0ruc Jun 5, 2025
3617a62
Add files via upload
ll0ruc Jun 5, 2025
cab90d1
Add files via upload
ll0ruc Jun 5, 2025
2f34a02
Update R2MEDMedicalSciencesRetrieval.json
ll0ruc Jun 5, 2025
a296c5f
Update R2MEDMedicalSciencesRetrieval.json
ll0ruc Jun 5, 2025
28354dc
Update R2MEDMedicalSciencesRetrieval.json
ll0ruc Jun 5, 2025
c9ee57a
Update R2MEDMedicalSciencesRetrieval.json
ll0ruc Jun 5, 2025
ad1440a
Update R2MEDMedicalSciencesRetrieval.json
ll0ruc Jun 5, 2025
2d8fdde
Update R2MEDMedicalSciencesRetrieval.json
ll0ruc Jun 5, 2025
449a51d
Update R2MEDMedicalSciencesRetrieval.json
ll0ruc Jun 5, 2025
bb4ae8c
Update R2MEDMedicalSciencesRetrieval.json
ll0ruc Jun 5, 2025
72f9c83
Update R2MEDMedicalSciencesRetrieval.json
ll0ruc Jun 5, 2025
bc87377
Update R2MEDMedicalSciencesRetrieval.json
ll0ruc Jun 5, 2025
59491ac
Update R2MEDMedicalSciencesRetrieval.json
ll0ruc Jun 5, 2025
f2e3aed
Update R2MEDMedicalSciencesRetrieval.json
ll0ruc Jun 5, 2025
6fdabc7
Update R2MEDMedicalSciencesRetrieval.json
ll0ruc Jun 5, 2025
40c15c8
Update R2MEDMedicalSciencesRetrieval.json
ll0ruc Jun 5, 2025
62cdc4b
Update R2MEDMedicalSciencesRetrieval.json
ll0ruc Jun 5, 2025
6f7da65
Update R2MEDMedicalSciencesRetrieval.json
ll0ruc Jun 5, 2025
6f76ff8
Update R2MEDMedicalSciencesRetrieval.json
ll0ruc Jun 5, 2025
ac05aec
Update R2MEDMedicalSciencesRetrieval.json
ll0ruc Jun 5, 2025
1ea14a7
Update R2MEDMedicalSciencesRetrieval.json
ll0ruc Jun 5, 2025
d221fcf
Update R2MEDMedicalSciencesRetrieval.json
ll0ruc Jun 5, 2025
d6536f7
Add results for Qwen3-Embedding series models (#214)
afalf Jun 6, 2025
959f3e3
fixed mistake in create pr results
KennethEnevoldsen Jun 10, 2025
de51683
add geoembedding results (#215)
Hypothesis-Z Jun 10, 2025
60c42cf
add cadet results (#218)
manveertamber Jun 10, 2025
e93844e
add xyz model (#207)
fangxiaoquan Jun 10, 2025
bdd314c
Update LGAI-Embedding results (#219)
annamodels Jun 15, 2025
5b14515
init automate script (#220)
Samoed Jun 15, 2025
79c71ca
Added encodechka results (#182)
Samoed Jun 16, 2025
341be28
update script (#222)
Samoed Jun 22, 2025
bc97323
update results for giga-embeddings-instruct (#208)
ekolodin Jun 22, 2025
2bd2521
add KaLM-Team__KaLM-Embedding-X-0605 with new instruct
Jun 25, 2025
cdbf82f
add KaLM-Team__KaLM-Embedding-X-0605 with new instruct
Jun 25, 2025
19a6f35
Add files via upload
ll0ruc May 29, 2025
1601b6a
merge
Jun 25, 2025
47a248d
Add files via upload
ll0ruc May 29, 2025
cf3ebf6
add geoembedding results (#215)
Hypothesis-Z Jun 10, 2025
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
75 changes: 75 additions & 0 deletions .github/workflows/model-results-comparison.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,75 @@
name: Model Results Comparison

on:
pull_request_target:
types: [opened, synchronize, edited]
paths:
- 'results/**/*.json'
workflow_dispatch:
inputs:
reference_models:
description: 'Space-separated list of reference models for comparison'
required: true
type: string
default: 'intfloat/multilingual-e5-large google/gemini-embedding-001'
pull_request_number:
description: 'The pull request number to comment on (required if triggered manually)'
required: false
type: string

permissions:
contents: read
pull-requests: write

jobs:
compare-results:
runs-on: ubuntu-latest

steps:
- name: Checkout code
uses: actions/checkout@v4
with:
# IMPORTANT: For pull_request_target, check out the PR branch explicitly
ref: ${{ github.event.pull_request.head.sha }}
fetch-depth: 0

- name: Fetch origin main
run: git fetch origin main

- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: '3.10'

- name: Install dependencies
run: |
pip install git+https://github.com/embeddings-benchmark/mteb.git tabulate

- name: Generate model comparison
env:
REFERENCE_MODELS: ${{ github.event.inputs.reference_models || 'intfloat/multilingual-e5-large google/gemini-embedding-001' }}
run: |
python scripts/create_pr_results_comment.py --reference-models $REFERENCE_MODELS --output model-comparison.md

- name: Upload comparison report
uses: actions/upload-artifact@v4
with:
name: model-comparison
path: model-comparison.md

- name: Determine PR Number
id: pr_info
run: |
if [ "${{ github.event_name }}" == "pull_request_target" ]; then
echo "pr_number=${{ github.event.number }}" >> $GITHUB_OUTPUT
elif [ "${{ github.event_name }}" == "workflow_dispatch" ] && [ -n "${{ github.event.inputs.pull_request_number }}" ]; then
echo "pr_number=${{ github.event.inputs.pull_request_number }}" >> $GITHUB_OUTPUT
else
echo "pr_number=" >> $GITHUB_OUTPUT
fi

- name: Post PR comment
if: steps.pr_info.outputs.pr_number != ''
env:
GITHUB_TOKEN: ${{ github.token }}
run: gh pr comment ${{ steps.pr_info.outputs.pr_number }} --body-file model-comparison.md --create-if-none --edit-last
Original file line number Diff line number Diff line change
@@ -0,0 +1,158 @@
{
"dataset_revision": "6021fce366892cbfd7837fa85a4128ea93315e18",
"task_name": "R2MEDBioinformaticsRetrieval",
"mteb_version": "1.38.20",
"scores": {
"test": [
{
"ndcg_at_1": 0.33766,
"ndcg_at_3": 0.3315,
"ndcg_at_5": 0.38632,
"ndcg_at_10": 0.42491,
"ndcg_at_20": 0.45599,
"ndcg_at_100": 0.50643,
"ndcg_at_1000": 0.53475,
"map_at_1": 0.15813,
"map_at_3": 0.24478,
"map_at_5": 0.29691,
"map_at_10": 0.32723,
"map_at_20": 0.34036,
"map_at_100": 0.35319,
"map_at_1000": 0.35551,
"recall_at_1": 0.15813,
"recall_at_3": 0.31487,
"recall_at_5": 0.45441,
"recall_at_10": 0.56146,
"recall_at_20": 0.64712,
"recall_at_100": 0.8287,
"recall_at_1000": 0.99382,
"precision_at_1": 0.33766,
"precision_at_3": 0.22078,
"precision_at_5": 0.21039,
"precision_at_10": 0.14156,
"precision_at_20": 0.08636,
"precision_at_100": 0.02429,
"precision_at_1000": 0.00292,
"mrr_at_1": 0.337662,
"mrr_at_3": 0.422078,
"mrr_at_5": 0.448701,
"mrr_at_10": 0.459699,
"mrr_at_20": 0.464088,
"mrr_at_100": 0.467727,
"mrr_at_1000": 0.468137,
"nauc_ndcg_at_1_max": 0.107933,
"nauc_ndcg_at_1_std": -0.036251,
"nauc_ndcg_at_1_diff1": 0.20485,
"nauc_ndcg_at_3_max": 0.003896,
"nauc_ndcg_at_3_std": -0.159925,
"nauc_ndcg_at_3_diff1": 0.158787,
"nauc_ndcg_at_5_max": -0.024326,
"nauc_ndcg_at_5_std": -0.259057,
"nauc_ndcg_at_5_diff1": 0.087966,
"nauc_ndcg_at_10_max": 0.046541,
"nauc_ndcg_at_10_std": -0.216917,
"nauc_ndcg_at_10_diff1": 0.102002,
"nauc_ndcg_at_20_max": 0.08808,
"nauc_ndcg_at_20_std": -0.193759,
"nauc_ndcg_at_20_diff1": 0.123764,
"nauc_ndcg_at_100_max": 0.101127,
"nauc_ndcg_at_100_std": -0.140113,
"nauc_ndcg_at_100_diff1": 0.094295,
"nauc_ndcg_at_1000_max": 0.105675,
"nauc_ndcg_at_1000_std": -0.119119,
"nauc_ndcg_at_1000_diff1": 0.122725,
"nauc_map_at_1_max": -0.128017,
"nauc_map_at_1_std": -0.228048,
"nauc_map_at_1_diff1": 0.206813,
"nauc_map_at_3_max": -0.077104,
"nauc_map_at_3_std": -0.271212,
"nauc_map_at_3_diff1": 0.163482,
"nauc_map_at_5_max": -0.051938,
"nauc_map_at_5_std": -0.301827,
"nauc_map_at_5_diff1": 0.10682,
"nauc_map_at_10_max": 0.009518,
"nauc_map_at_10_std": -0.253407,
"nauc_map_at_10_diff1": 0.119989,
"nauc_map_at_20_max": 0.027802,
"nauc_map_at_20_std": -0.240282,
"nauc_map_at_20_diff1": 0.128026,
"nauc_map_at_100_max": 0.036107,
"nauc_map_at_100_std": -0.222729,
"nauc_map_at_100_diff1": 0.120636,
"nauc_map_at_1000_max": 0.035463,
"nauc_map_at_1000_std": -0.220357,
"nauc_map_at_1000_diff1": 0.122269,
"nauc_recall_at_1_max": -0.128017,
"nauc_recall_at_1_std": -0.228048,
"nauc_recall_at_1_diff1": 0.206813,
"nauc_recall_at_3_max": -0.092021,
"nauc_recall_at_3_std": -0.277492,
"nauc_recall_at_3_diff1": 0.137652,
"nauc_recall_at_5_max": -0.114084,
"nauc_recall_at_5_std": -0.409315,
"nauc_recall_at_5_diff1": -0.005854,
"nauc_recall_at_10_max": -0.005245,
"nauc_recall_at_10_std": -0.310963,
"nauc_recall_at_10_diff1": 0.003225,
"nauc_recall_at_20_max": 0.092056,
"nauc_recall_at_20_std": -0.296093,
"nauc_recall_at_20_diff1": 0.075963,
"nauc_recall_at_100_max": 0.087527,
"nauc_recall_at_100_std": -0.212826,
"nauc_recall_at_100_diff1": -0.104752,
"nauc_recall_at_1000_max": -0.431216,
"nauc_recall_at_1000_std": -1.730542,
"nauc_recall_at_1000_diff1": -0.013341,
"nauc_precision_at_1_max": 0.107933,
"nauc_precision_at_1_std": -0.036251,
"nauc_precision_at_1_diff1": 0.20485,
"nauc_precision_at_3_max": 0.169329,
"nauc_precision_at_3_std": -0.048836,
"nauc_precision_at_3_diff1": 0.120776,
"nauc_precision_at_5_max": 0.159786,
"nauc_precision_at_5_std": -0.050926,
"nauc_precision_at_5_diff1": -0.036858,
"nauc_precision_at_10_max": 0.274123,
"nauc_precision_at_10_std": 0.126855,
"nauc_precision_at_10_diff1": -0.026095,
"nauc_precision_at_20_max": 0.332965,
"nauc_precision_at_20_std": 0.222284,
"nauc_precision_at_20_diff1": -0.010906,
"nauc_precision_at_100_max": 0.306047,
"nauc_precision_at_100_std": 0.407784,
"nauc_precision_at_100_diff1": -0.111434,
"nauc_precision_at_1000_max": 0.310909,
"nauc_precision_at_1000_std": 0.502172,
"nauc_precision_at_1000_diff1": -0.022547,
"nauc_mrr_at_1_max": 0.107933,
"nauc_mrr_at_1_std": -0.036251,
"nauc_mrr_at_1_diff1": 0.20485,
"nauc_mrr_at_3_max": 0.133737,
"nauc_mrr_at_3_std": -0.020626,
"nauc_mrr_at_3_diff1": 0.198239,
"nauc_mrr_at_5_max": 0.118186,
"nauc_mrr_at_5_std": -0.052252,
"nauc_mrr_at_5_diff1": 0.164958,
"nauc_mrr_at_10_max": 0.123855,
"nauc_mrr_at_10_std": -0.036904,
"nauc_mrr_at_10_diff1": 0.161794,
"nauc_mrr_at_20_max": 0.132658,
"nauc_mrr_at_20_std": -0.031363,
"nauc_mrr_at_20_diff1": 0.165566,
"nauc_mrr_at_100_max": 0.129236,
"nauc_mrr_at_100_std": -0.033646,
"nauc_mrr_at_100_diff1": 0.166151,
"nauc_mrr_at_1000_max": 0.12938,
"nauc_mrr_at_1000_std": -0.03328,
"nauc_mrr_at_1000_diff1": 0.16674,
"main_score": 0.42491,
"hf_subset": "default",
"languages": [
"eng-Latn"
]
}
]
},
"evaluation_time": 76.0640599639842,
"kg_co2_emissions": null
}
Original file line number Diff line number Diff line change
@@ -0,0 +1,158 @@
{
"dataset_revision": "8b9fec2db9eda4b5742d03732213fbaee8169556",
"task_name": "R2MEDBiologyRetrieval",
"mteb_version": "1.38.20",
"scores": {
"test": [
{
"ndcg_at_1": 0.15534,
"ndcg_at_3": 0.15733,
"ndcg_at_5": 0.15068,
"ndcg_at_10": 0.17158,
"ndcg_at_20": 0.20041,
"ndcg_at_100": 0.26314,
"ndcg_at_1000": 0.32761,
"map_at_1": 0.0376,
"map_at_3": 0.08401,
"map_at_5": 0.09239,
"map_at_10": 0.11209,
"map_at_20": 0.12309,
"map_at_100": 0.13613,
"map_at_1000": 0.13986,
"recall_at_1": 0.0376,
"recall_at_3": 0.12183,
"recall_at_5": 0.1426,
"recall_at_10": 0.20792,
"recall_at_20": 0.28802,
"recall_at_100": 0.52119,
"recall_at_1000": 0.88396,
"precision_at_1": 0.15534,
"precision_at_3": 0.14239,
"precision_at_5": 0.1068,
"precision_at_10": 0.08155,
"precision_at_20": 0.05534,
"precision_at_100": 0.02,
"precision_at_1000": 0.00324,
"mrr_at_1": 0.135922,
"mrr_at_3": 0.203883,
"mrr_at_5": 0.212621,
"mrr_at_10": 0.224149,
"mrr_at_20": 0.230638,
"mrr_at_100": 0.23588,
"mrr_at_1000": 0.236849,
"nauc_ndcg_at_1_max": 0.043162,
"nauc_ndcg_at_1_std": -0.197054,
"nauc_ndcg_at_1_diff1": 0.033,
"nauc_ndcg_at_3_max": 0.036832,
"nauc_ndcg_at_3_std": -0.217969,
"nauc_ndcg_at_3_diff1": 0.042707,
"nauc_ndcg_at_5_max": 0.083252,
"nauc_ndcg_at_5_std": -0.209761,
"nauc_ndcg_at_5_diff1": 0.076015,
"nauc_ndcg_at_10_max": 0.109022,
"nauc_ndcg_at_10_std": -0.179232,
"nauc_ndcg_at_10_diff1": 0.090936,
"nauc_ndcg_at_20_max": 0.055902,
"nauc_ndcg_at_20_std": -0.219545,
"nauc_ndcg_at_20_diff1": 0.056387,
"nauc_ndcg_at_100_max": 0.007695,
"nauc_ndcg_at_100_std": -0.243414,
"nauc_ndcg_at_100_diff1": 0.027337,
"nauc_ndcg_at_1000_max": 0.04756,
"nauc_ndcg_at_1000_std": -0.179507,
"nauc_ndcg_at_1000_diff1": 0.022172,
"nauc_map_at_1_max": 0.152888,
"nauc_map_at_1_std": -0.206546,
"nauc_map_at_1_diff1": 0.067181,
"nauc_map_at_3_max": 0.133551,
"nauc_map_at_3_std": -0.234395,
"nauc_map_at_3_diff1": 0.074463,
"nauc_map_at_5_max": 0.146198,
"nauc_map_at_5_std": -0.219463,
"nauc_map_at_5_diff1": 0.090968,
"nauc_map_at_10_max": 0.127698,
"nauc_map_at_10_std": -0.211415,
"nauc_map_at_10_diff1": 0.105176,
"nauc_map_at_20_max": 0.091347,
"nauc_map_at_20_std": -0.227329,
"nauc_map_at_20_diff1": 0.070797,
"nauc_map_at_100_max": 0.07235,
"nauc_map_at_100_std": -0.228508,
"nauc_map_at_100_diff1": 0.059918,
"nauc_map_at_1000_max": 0.073293,
"nauc_map_at_1000_std": -0.224687,
"nauc_map_at_1000_diff1": 0.058591,
"nauc_recall_at_1_max": 0.152888,
"nauc_recall_at_1_std": -0.206546,
"nauc_recall_at_1_diff1": 0.067181,
"nauc_recall_at_3_max": 0.158256,
"nauc_recall_at_3_std": -0.198852,
"nauc_recall_at_3_diff1": 0.135204,
"nauc_recall_at_5_max": 0.205718,
"nauc_recall_at_5_std": -0.170234,
"nauc_recall_at_5_diff1": 0.168633,
"nauc_recall_at_10_max": 0.175269,
"nauc_recall_at_10_std": -0.125935,
"nauc_recall_at_10_diff1": 0.14925,
"nauc_recall_at_20_max": 0.045362,
"nauc_recall_at_20_std": -0.209459,
"nauc_recall_at_20_diff1": 0.063763,
"nauc_recall_at_100_max": -0.093978,
"nauc_recall_at_100_std": -0.289285,
"nauc_recall_at_100_diff1": -0.012271,
"nauc_recall_at_1000_max": 0.205614,
"nauc_recall_at_1000_std": 0.315539,
"nauc_recall_at_1000_diff1": -0.052651,
"nauc_precision_at_1_max": 0.043162,
"nauc_precision_at_1_std": -0.197054,
"nauc_precision_at_1_diff1": 0.033,
"nauc_precision_at_3_max": -0.034286,
"nauc_precision_at_3_std": -0.231688,
"nauc_precision_at_3_diff1": 0.004616,
"nauc_precision_at_5_max": -0.012642,
"nauc_precision_at_5_std": -0.198358,
"nauc_precision_at_5_diff1": 0.016286,
"nauc_precision_at_10_max": -0.036443,
"nauc_precision_at_10_std": -0.174946,
"nauc_precision_at_10_diff1": 0.034214,
"nauc_precision_at_20_max": -0.125512,
"nauc_precision_at_20_std": -0.214498,
"nauc_precision_at_20_diff1": -0.051533,
"nauc_precision_at_100_max": -0.177078,
"nauc_precision_at_100_std": -0.18669,
"nauc_precision_at_100_diff1": -0.090969,
"nauc_precision_at_1000_max": -0.126668,
"nauc_precision_at_1000_std": -0.038646,
"nauc_precision_at_1000_diff1": -0.124093,
"nauc_mrr_at_1_max": 0.047079,
"nauc_mrr_at_1_std": -0.179281,
"nauc_mrr_at_1_diff1": 0.127084,
"nauc_mrr_at_3_max": 0.041883,
"nauc_mrr_at_3_std": -0.214568,
"nauc_mrr_at_3_diff1": 0.083644,
"nauc_mrr_at_5_max": 0.058587,
"nauc_mrr_at_5_std": -0.204153,
"nauc_mrr_at_5_diff1": 0.077505,
"nauc_mrr_at_10_max": 0.055233,
"nauc_mrr_at_10_std": -0.185858,
"nauc_mrr_at_10_diff1": 0.065808,
"nauc_mrr_at_20_max": 0.053161,
"nauc_mrr_at_20_std": -0.19455,
"nauc_mrr_at_20_diff1": 0.076221,
"nauc_mrr_at_100_max": 0.04739,
"nauc_mrr_at_100_std": -0.200545,
"nauc_mrr_at_100_diff1": 0.074901,
"nauc_mrr_at_1000_max": 0.047993,
"nauc_mrr_at_1000_std": -0.199493,
"nauc_mrr_at_1000_diff1": 0.074695,
"main_score": 0.17158,
"hf_subset": "default",
"languages": [
"eng-Latn"
]
}
]
},
"evaluation_time": 55.14279148916425,
"kg_co2_emissions": null
}
Loading
Loading