GritLM-7B / README.md
leaderboard-pr-bot's picture
Adding Evaluation Results
0fc115c verified
|
raw
history blame
64.3 kB
---
license: apache-2.0
tags:
- mteb
datasets:
- GritLM/tulu2
pipeline_tag: text-generation
inference: true
model-index:
- name: GritLM-7B
results:
- task:
type: Classification
dataset:
name: MTEB AmazonCounterfactualClassification (en)
type: mteb/amazon_counterfactual
config: en
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 81.17910447761194
- type: ap
value: 46.26260671758199
- type: f1
value: 75.44565719934167
- task:
type: Classification
dataset:
name: MTEB AmazonPolarityClassification
type: mteb/amazon_polarity
config: default
split: test
revision: e2d317d38cd51312af73b3d32a06d1a08b442046
metrics:
- type: accuracy
value: 96.5161
- type: ap
value: 94.79131981460425
- type: f1
value: 96.51506148413065
- task:
type: Classification
dataset:
name: MTEB AmazonReviewsClassification (en)
type: mteb/amazon_reviews_multi
config: en
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 57.806000000000004
- type: f1
value: 56.78350156257903
- task:
type: Retrieval
dataset:
name: MTEB ArguAna
type: arguana
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 38.478
- type: map_at_10
value: 54.955
- type: map_at_100
value: 54.955
- type: map_at_1000
value: 54.955
- type: map_at_3
value: 50.888999999999996
- type: map_at_5
value: 53.349999999999994
- type: mrr_at_1
value: 39.757999999999996
- type: mrr_at_10
value: 55.449000000000005
- type: mrr_at_100
value: 55.449000000000005
- type: mrr_at_1000
value: 55.449000000000005
- type: mrr_at_3
value: 51.37500000000001
- type: mrr_at_5
value: 53.822
- type: ndcg_at_1
value: 38.478
- type: ndcg_at_10
value: 63.239999999999995
- type: ndcg_at_100
value: 63.239999999999995
- type: ndcg_at_1000
value: 63.239999999999995
- type: ndcg_at_3
value: 54.935
- type: ndcg_at_5
value: 59.379000000000005
- type: precision_at_1
value: 38.478
- type: precision_at_10
value: 8.933
- type: precision_at_100
value: 0.893
- type: precision_at_1000
value: 0.089
- type: precision_at_3
value: 22.214
- type: precision_at_5
value: 15.491
- type: recall_at_1
value: 38.478
- type: recall_at_10
value: 89.331
- type: recall_at_100
value: 89.331
- type: recall_at_1000
value: 89.331
- type: recall_at_3
value: 66.643
- type: recall_at_5
value: 77.45400000000001
- task:
type: Clustering
dataset:
name: MTEB ArxivClusteringP2P
type: mteb/arxiv-clustering-p2p
config: default
split: test
revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d
metrics:
- type: v_measure
value: 51.67144081472449
- task:
type: Clustering
dataset:
name: MTEB ArxivClusteringS2S
type: mteb/arxiv-clustering-s2s
config: default
split: test
revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53
metrics:
- type: v_measure
value: 48.11256154264126
- task:
type: Reranking
dataset:
name: MTEB AskUbuntuDupQuestions
type: mteb/askubuntudupquestions-reranking
config: default
split: test
revision: 2000358ca161889fa9c082cb41daa8dcfb161a54
metrics:
- type: map
value: 67.33801955487878
- type: mrr
value: 80.71549487754474
- task:
type: STS
dataset:
name: MTEB BIOSSES
type: mteb/biosses-sts
config: default
split: test
revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
metrics:
- type: cos_sim_pearson
value: 88.1935203751726
- type: cos_sim_spearman
value: 86.35497970498659
- type: euclidean_pearson
value: 85.46910708503744
- type: euclidean_spearman
value: 85.13928935405485
- type: manhattan_pearson
value: 85.68373836333303
- type: manhattan_spearman
value: 85.40013867117746
- task:
type: Classification
dataset:
name: MTEB Banking77Classification
type: mteb/banking77
config: default
split: test
revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
metrics:
- type: accuracy
value: 88.46753246753248
- type: f1
value: 88.43006344981134
- task:
type: Clustering
dataset:
name: MTEB BiorxivClusteringP2P
type: mteb/biorxiv-clustering-p2p
config: default
split: test
revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40
metrics:
- type: v_measure
value: 40.86793640310432
- task:
type: Clustering
dataset:
name: MTEB BiorxivClusteringS2S
type: mteb/biorxiv-clustering-s2s
config: default
split: test
revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908
metrics:
- type: v_measure
value: 39.80291334130727
- task:
type: Retrieval
dataset:
name: MTEB CQADupstackAndroidRetrieval
type: BeIR/cqadupstack
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 38.421
- type: map_at_10
value: 52.349000000000004
- type: map_at_100
value: 52.349000000000004
- type: map_at_1000
value: 52.349000000000004
- type: map_at_3
value: 48.17
- type: map_at_5
value: 50.432
- type: mrr_at_1
value: 47.353
- type: mrr_at_10
value: 58.387
- type: mrr_at_100
value: 58.387
- type: mrr_at_1000
value: 58.387
- type: mrr_at_3
value: 56.199
- type: mrr_at_5
value: 57.487
- type: ndcg_at_1
value: 47.353
- type: ndcg_at_10
value: 59.202
- type: ndcg_at_100
value: 58.848
- type: ndcg_at_1000
value: 58.831999999999994
- type: ndcg_at_3
value: 54.112
- type: ndcg_at_5
value: 56.312
- type: precision_at_1
value: 47.353
- type: precision_at_10
value: 11.459
- type: precision_at_100
value: 1.146
- type: precision_at_1000
value: 0.11499999999999999
- type: precision_at_3
value: 26.133
- type: precision_at_5
value: 18.627
- type: recall_at_1
value: 38.421
- type: recall_at_10
value: 71.89
- type: recall_at_100
value: 71.89
- type: recall_at_1000
value: 71.89
- type: recall_at_3
value: 56.58
- type: recall_at_5
value: 63.125
- type: map_at_1
value: 38.025999999999996
- type: map_at_10
value: 50.590999999999994
- type: map_at_100
value: 51.99700000000001
- type: map_at_1000
value: 52.11599999999999
- type: map_at_3
value: 47.435
- type: map_at_5
value: 49.236000000000004
- type: mrr_at_1
value: 48.28
- type: mrr_at_10
value: 56.814
- type: mrr_at_100
value: 57.446
- type: mrr_at_1000
value: 57.476000000000006
- type: mrr_at_3
value: 54.958
- type: mrr_at_5
value: 56.084999999999994
- type: ndcg_at_1
value: 48.28
- type: ndcg_at_10
value: 56.442
- type: ndcg_at_100
value: 60.651999999999994
- type: ndcg_at_1000
value: 62.187000000000005
- type: ndcg_at_3
value: 52.866
- type: ndcg_at_5
value: 54.515
- type: precision_at_1
value: 48.28
- type: precision_at_10
value: 10.586
- type: precision_at_100
value: 1.6310000000000002
- type: precision_at_1000
value: 0.20600000000000002
- type: precision_at_3
value: 25.945
- type: precision_at_5
value: 18.076
- type: recall_at_1
value: 38.025999999999996
- type: recall_at_10
value: 66.11399999999999
- type: recall_at_100
value: 83.339
- type: recall_at_1000
value: 92.413
- type: recall_at_3
value: 54.493
- type: recall_at_5
value: 59.64699999999999
- type: map_at_1
value: 47.905
- type: map_at_10
value: 61.58
- type: map_at_100
value: 62.605
- type: map_at_1000
value: 62.637
- type: map_at_3
value: 58.074000000000005
- type: map_at_5
value: 60.260000000000005
- type: mrr_at_1
value: 54.42
- type: mrr_at_10
value: 64.847
- type: mrr_at_100
value: 65.403
- type: mrr_at_1000
value: 65.41900000000001
- type: mrr_at_3
value: 62.675000000000004
- type: mrr_at_5
value: 64.101
- type: ndcg_at_1
value: 54.42
- type: ndcg_at_10
value: 67.394
- type: ndcg_at_100
value: 70.846
- type: ndcg_at_1000
value: 71.403
- type: ndcg_at_3
value: 62.025
- type: ndcg_at_5
value: 65.032
- type: precision_at_1
value: 54.42
- type: precision_at_10
value: 10.646
- type: precision_at_100
value: 1.325
- type: precision_at_1000
value: 0.13999999999999999
- type: precision_at_3
value: 27.398
- type: precision_at_5
value: 18.796
- type: recall_at_1
value: 47.905
- type: recall_at_10
value: 80.84599999999999
- type: recall_at_100
value: 95.078
- type: recall_at_1000
value: 98.878
- type: recall_at_3
value: 67.05600000000001
- type: recall_at_5
value: 74.261
- type: map_at_1
value: 30.745
- type: map_at_10
value: 41.021
- type: map_at_100
value: 41.021
- type: map_at_1000
value: 41.021
- type: map_at_3
value: 37.714999999999996
- type: map_at_5
value: 39.766
- type: mrr_at_1
value: 33.559
- type: mrr_at_10
value: 43.537
- type: mrr_at_100
value: 43.537
- type: mrr_at_1000
value: 43.537
- type: mrr_at_3
value: 40.546
- type: mrr_at_5
value: 42.439
- type: ndcg_at_1
value: 33.559
- type: ndcg_at_10
value: 46.781
- type: ndcg_at_100
value: 46.781
- type: ndcg_at_1000
value: 46.781
- type: ndcg_at_3
value: 40.516000000000005
- type: ndcg_at_5
value: 43.957
- type: precision_at_1
value: 33.559
- type: precision_at_10
value: 7.198
- type: precision_at_100
value: 0.72
- type: precision_at_1000
value: 0.07200000000000001
- type: precision_at_3
value: 17.1
- type: precision_at_5
value: 12.316
- type: recall_at_1
value: 30.745
- type: recall_at_10
value: 62.038000000000004
- type: recall_at_100
value: 62.038000000000004
- type: recall_at_1000
value: 62.038000000000004
- type: recall_at_3
value: 45.378
- type: recall_at_5
value: 53.580000000000005
- type: map_at_1
value: 19.637999999999998
- type: map_at_10
value: 31.05
- type: map_at_100
value: 31.05
- type: map_at_1000
value: 31.05
- type: map_at_3
value: 27.628000000000004
- type: map_at_5
value: 29.767
- type: mrr_at_1
value: 25.0
- type: mrr_at_10
value: 36.131
- type: mrr_at_100
value: 36.131
- type: mrr_at_1000
value: 36.131
- type: mrr_at_3
value: 33.333
- type: mrr_at_5
value: 35.143
- type: ndcg_at_1
value: 25.0
- type: ndcg_at_10
value: 37.478
- type: ndcg_at_100
value: 37.469
- type: ndcg_at_1000
value: 37.469
- type: ndcg_at_3
value: 31.757999999999996
- type: ndcg_at_5
value: 34.821999999999996
- type: precision_at_1
value: 25.0
- type: precision_at_10
value: 7.188999999999999
- type: precision_at_100
value: 0.719
- type: precision_at_1000
value: 0.07200000000000001
- type: precision_at_3
value: 15.837000000000002
- type: precision_at_5
value: 11.841
- type: recall_at_1
value: 19.637999999999998
- type: recall_at_10
value: 51.836000000000006
- type: recall_at_100
value: 51.836000000000006
- type: recall_at_1000
value: 51.836000000000006
- type: recall_at_3
value: 36.384
- type: recall_at_5
value: 43.964
- type: map_at_1
value: 34.884
- type: map_at_10
value: 47.88
- type: map_at_100
value: 47.88
- type: map_at_1000
value: 47.88
- type: map_at_3
value: 43.85
- type: map_at_5
value: 46.414
- type: mrr_at_1
value: 43.022
- type: mrr_at_10
value: 53.569
- type: mrr_at_100
value: 53.569
- type: mrr_at_1000
value: 53.569
- type: mrr_at_3
value: 51.075
- type: mrr_at_5
value: 52.725
- type: ndcg_at_1
value: 43.022
- type: ndcg_at_10
value: 54.461000000000006
- type: ndcg_at_100
value: 54.388000000000005
- type: ndcg_at_1000
value: 54.388000000000005
- type: ndcg_at_3
value: 48.864999999999995
- type: ndcg_at_5
value: 52.032000000000004
- type: precision_at_1
value: 43.022
- type: precision_at_10
value: 9.885
- type: precision_at_100
value: 0.988
- type: precision_at_1000
value: 0.099
- type: precision_at_3
value: 23.612
- type: precision_at_5
value: 16.997
- type: recall_at_1
value: 34.884
- type: recall_at_10
value: 68.12899999999999
- type: recall_at_100
value: 68.12899999999999
- type: recall_at_1000
value: 68.12899999999999
- type: recall_at_3
value: 52.428
- type: recall_at_5
value: 60.662000000000006
- type: map_at_1
value: 31.588
- type: map_at_10
value: 43.85
- type: map_at_100
value: 45.317
- type: map_at_1000
value: 45.408
- type: map_at_3
value: 39.73
- type: map_at_5
value: 42.122
- type: mrr_at_1
value: 38.927
- type: mrr_at_10
value: 49.582
- type: mrr_at_100
value: 50.39
- type: mrr_at_1000
value: 50.426
- type: mrr_at_3
value: 46.518
- type: mrr_at_5
value: 48.271
- type: ndcg_at_1
value: 38.927
- type: ndcg_at_10
value: 50.605999999999995
- type: ndcg_at_100
value: 56.22200000000001
- type: ndcg_at_1000
value: 57.724
- type: ndcg_at_3
value: 44.232
- type: ndcg_at_5
value: 47.233999999999995
- type: precision_at_1
value: 38.927
- type: precision_at_10
value: 9.429
- type: precision_at_100
value: 1.435
- type: precision_at_1000
value: 0.172
- type: precision_at_3
value: 21.271
- type: precision_at_5
value: 15.434000000000001
- type: recall_at_1
value: 31.588
- type: recall_at_10
value: 64.836
- type: recall_at_100
value: 88.066
- type: recall_at_1000
value: 97.748
- type: recall_at_3
value: 47.128
- type: recall_at_5
value: 54.954
- type: map_at_1
value: 31.956083333333336
- type: map_at_10
value: 43.33483333333333
- type: map_at_100
value: 44.64883333333333
- type: map_at_1000
value: 44.75
- type: map_at_3
value: 39.87741666666666
- type: map_at_5
value: 41.86766666666667
- type: mrr_at_1
value: 38.06341666666667
- type: mrr_at_10
value: 47.839666666666666
- type: mrr_at_100
value: 48.644000000000005
- type: mrr_at_1000
value: 48.68566666666667
- type: mrr_at_3
value: 45.26358333333334
- type: mrr_at_5
value: 46.790000000000006
- type: ndcg_at_1
value: 38.06341666666667
- type: ndcg_at_10
value: 49.419333333333334
- type: ndcg_at_100
value: 54.50166666666667
- type: ndcg_at_1000
value: 56.161166666666674
- type: ndcg_at_3
value: 43.982416666666666
- type: ndcg_at_5
value: 46.638083333333334
- type: precision_at_1
value: 38.06341666666667
- type: precision_at_10
value: 8.70858333333333
- type: precision_at_100
value: 1.327
- type: precision_at_1000
value: 0.165
- type: precision_at_3
value: 20.37816666666667
- type: precision_at_5
value: 14.516333333333334
- type: recall_at_1
value: 31.956083333333336
- type: recall_at_10
value: 62.69458333333334
- type: recall_at_100
value: 84.46433333333334
- type: recall_at_1000
value: 95.58449999999999
- type: recall_at_3
value: 47.52016666666666
- type: recall_at_5
value: 54.36066666666666
- type: map_at_1
value: 28.912
- type: map_at_10
value: 38.291
- type: map_at_100
value: 39.44
- type: map_at_1000
value: 39.528
- type: map_at_3
value: 35.638
- type: map_at_5
value: 37.218
- type: mrr_at_1
value: 32.822
- type: mrr_at_10
value: 41.661
- type: mrr_at_100
value: 42.546
- type: mrr_at_1000
value: 42.603
- type: mrr_at_3
value: 39.238
- type: mrr_at_5
value: 40.726
- type: ndcg_at_1
value: 32.822
- type: ndcg_at_10
value: 43.373
- type: ndcg_at_100
value: 48.638
- type: ndcg_at_1000
value: 50.654999999999994
- type: ndcg_at_3
value: 38.643
- type: ndcg_at_5
value: 41.126000000000005
- type: precision_at_1
value: 32.822
- type: precision_at_10
value: 6.8709999999999996
- type: precision_at_100
value: 1.032
- type: precision_at_1000
value: 0.128
- type: precision_at_3
value: 16.82
- type: precision_at_5
value: 11.718
- type: recall_at_1
value: 28.912
- type: recall_at_10
value: 55.376999999999995
- type: recall_at_100
value: 79.066
- type: recall_at_1000
value: 93.664
- type: recall_at_3
value: 42.569
- type: recall_at_5
value: 48.719
- type: map_at_1
value: 22.181
- type: map_at_10
value: 31.462
- type: map_at_100
value: 32.73
- type: map_at_1000
value: 32.848
- type: map_at_3
value: 28.57
- type: map_at_5
value: 30.182
- type: mrr_at_1
value: 27.185
- type: mrr_at_10
value: 35.846000000000004
- type: mrr_at_100
value: 36.811
- type: mrr_at_1000
value: 36.873
- type: mrr_at_3
value: 33.437
- type: mrr_at_5
value: 34.813
- type: ndcg_at_1
value: 27.185
- type: ndcg_at_10
value: 36.858000000000004
- type: ndcg_at_100
value: 42.501
- type: ndcg_at_1000
value: 44.945
- type: ndcg_at_3
value: 32.066
- type: ndcg_at_5
value: 34.29
- type: precision_at_1
value: 27.185
- type: precision_at_10
value: 6.752
- type: precision_at_100
value: 1.111
- type: precision_at_1000
value: 0.151
- type: precision_at_3
value: 15.290000000000001
- type: precision_at_5
value: 11.004999999999999
- type: recall_at_1
value: 22.181
- type: recall_at_10
value: 48.513
- type: recall_at_100
value: 73.418
- type: recall_at_1000
value: 90.306
- type: recall_at_3
value: 35.003
- type: recall_at_5
value: 40.876000000000005
- type: map_at_1
value: 33.934999999999995
- type: map_at_10
value: 44.727
- type: map_at_100
value: 44.727
- type: map_at_1000
value: 44.727
- type: map_at_3
value: 40.918
- type: map_at_5
value: 42.961
- type: mrr_at_1
value: 39.646
- type: mrr_at_10
value: 48.898
- type: mrr_at_100
value: 48.898
- type: mrr_at_1000
value: 48.898
- type: mrr_at_3
value: 45.896
- type: mrr_at_5
value: 47.514
- type: ndcg_at_1
value: 39.646
- type: ndcg_at_10
value: 50.817
- type: ndcg_at_100
value: 50.803
- type: ndcg_at_1000
value: 50.803
- type: ndcg_at_3
value: 44.507999999999996
- type: ndcg_at_5
value: 47.259
- type: precision_at_1
value: 39.646
- type: precision_at_10
value: 8.759
- type: precision_at_100
value: 0.876
- type: precision_at_1000
value: 0.08800000000000001
- type: precision_at_3
value: 20.274
- type: precision_at_5
value: 14.366000000000001
- type: recall_at_1
value: 33.934999999999995
- type: recall_at_10