Skip to content

Add IBM Granite Embedding Model results #74

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Samoed merged 2 commits into from
Dec 19, 2024
Merged

Add IBM Granite Embedding Model results #74

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8ec3df2
add results for IBM Granite Embeddings
aashka-trivedi Dec 18, 2024
cccf8e1
update model_meta.json for IBM granite embedding models
aashka-trivedi Dec 18, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
179 changes: 179 additions & 0 deletions ...ilingual/47db56afe692f731540413c67dd818ff492277e7/AmazonCounterfactualClassification.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,179 @@
{
"dataset_revision": "e8379541af4e31359cca9fbcf4b00f2671dba205",
"task_name": "AmazonCounterfactualClassification",
"mteb_version": "1.24.0",
"scores": {
"test": [
{
"accuracy": 0.727136,
"f1": 0.604454,
"f1_weighted": 0.778541,
"ap": 0.224958,
"ap_weighted": 0.224958,
"scores_per_experiment": [
{
"accuracy": 0.777361,
"f1": 0.649857,
"f1_weighted": 0.817117,
"ap": 0.265461,
"ap_weighted": 0.265461
},
{
"accuracy": 0.67916,
"f1": 0.567419,
"f1_weighted": 0.741459,
"ap": 0.199585,
"ap_weighted": 0.199585
},
{
"accuracy": 0.705397,
"f1": 0.585717,
"f1_weighted": 0.761983,
"ap": 0.209036,
"ap_weighted": 0.209036
},
{
"accuracy": 0.665667,
"f1": 0.545468,
"f1_weighted": 0.730498,
"ap": 0.172667,
"ap_weighted": 0.172667
},
{
"accuracy": 0.743628,
"f1": 0.621385,
"f1_weighted": 0.791687,
"ap": 0.241851,
"ap_weighted": 0.241851
},
{
"accuracy": 0.745127,
"f1": 0.62169,
"f1_weighted": 0.792753,
"ap": 0.240811,
"ap_weighted": 0.240811
},
{
"accuracy": 0.734633,
"f1": 0.610057,
"f1_weighted": 0.784529,
"ap": 0.227797,
"ap_weighted": 0.227797
},
{
"accuracy": 0.737631,
"f1": 0.612529,
"f1_weighted": 0.786814,
"ap": 0.229704,
"ap_weighted": 0.229704
},
{
"accuracy": 0.711394,
"f1": 0.59415,
"f1_weighted": 0.766828,
"ap": 0.219764,
"ap_weighted": 0.219764
},
{
"accuracy": 0.771364,
"f1": 0.636264,
"f1_weighted": 0.811745,
"ap": 0.242908,
"ap_weighted": 0.242908
}
],
"main_score": 0.727136,
"hf_subset": "en-ext",
"languages": [
"eng-Latn"
]
},
{
"accuracy": 0.716716,
"f1": 0.654221,
"f1_weighted": 0.743533,
"ap": 0.337567,
"ap_weighted": 0.337567,
"scores_per_experiment": [
{
"accuracy": 0.726866,
"f1": 0.665485,
"f1_weighted": 0.752744,
"ap": 0.349189,
"ap_weighted": 0.349189
},
{
"accuracy": 0.744776,
"f1": 0.686435,
"f1_weighted": 0.768799,
"ap": 0.375447,
"ap_weighted": 0.375447
},
{
"accuracy": 0.683582,
"f1": 0.621142,
"f1_weighted": 0.714802,
"ap": 0.303993,
"ap_weighted": 0.303993
},
{
"accuracy": 0.698507,
"f1": 0.639012,
"f1_weighted": 0.728255,
"ap": 0.323834,
"ap_weighted": 0.323834
},
{
"accuracy": 0.722388,
"f1": 0.656187,
"f1_weighted": 0.748058,
"ap": 0.334928,
"ap_weighted": 0.334928
},
{
"accuracy": 0.695522,
"f1": 0.639561,
"f1_weighted": 0.726047,
"ap": 0.327941,
"ap_weighted": 0.327941
},
{
"accuracy": 0.783582,
"f1": 0.711443,
"f1_weighted": 0.799302,
"ap": 0.391443,
"ap_weighted": 0.391443
},
{
"accuracy": 0.729851,
"f1": 0.663784,
"f1_weighted": 0.754542,
"ap": 0.342946,
"ap_weighted": 0.342946
},
{
"accuracy": 0.704478,
"f1": 0.63975,
"f1_weighted": 0.732739,
"ap": 0.319735,
"ap_weighted": 0.319735
},
{
"accuracy": 0.677612,
"f1": 0.619414,
"f1_weighted": 0.710043,
"ap": 0.306214,
"ap_weighted": 0.306214
}
],
"main_score": 0.716716,
"hf_subset": "en",
"languages": [
"eng-Latn"
]
}
]
},
"evaluation_time": 6.15715217590332,
"kg_co2_emissions": null
}
95 changes: 95 additions & 0 deletions ...m-multilingual/47db56afe692f731540413c67dd818ff492277e7/AmazonPolarityClassification.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,95 @@
{
"dataset_revision": "e2d317d38cd51312af73b3d32a06d1a08b442046",
"task_name": "AmazonPolarityClassification",
"mteb_version": "1.24.0",
"scores": {
"test": [
{
"accuracy": 0.665804,
"f1": 0.662191,
"f1_weighted": 0.662191,
"ap": 0.613408,
"ap_weighted": 0.613408,
"scores_per_experiment": [
{
"accuracy": 0.674458,
"f1": 0.674065,
"f1_weighted": 0.674065,
"ap": 0.615689,
"ap_weighted": 0.615689
},
{
"accuracy": 0.615428,
"f1": 0.614583,
"f1_weighted": 0.614583,
"ap": 0.569897,
"ap_weighted": 0.569897
},
{
"accuracy": 0.701525,
"f1": 0.701524,
"f1_weighted": 0.701524,
"ap": 0.641251,
"ap_weighted": 0.641251
},
{
"accuracy": 0.640888,
"f1": 0.628752,
"f1_weighted": 0.628752,
"ap": 0.601536,
"ap_weighted": 0.601536
},
{
"accuracy": 0.72023,
"f1": 0.720134,
"f1_weighted": 0.720134,
"ap": 0.660481,
"ap_weighted": 0.660481
},
{
"accuracy": 0.672493,
"f1": 0.672028,
"f1_weighted": 0.672028,
"ap": 0.618422,
"ap_weighted": 0.618422
},
{
"accuracy": 0.642605,
"f1": 0.63658,
"f1_weighted": 0.63658,
"ap": 0.587474,
"ap_weighted": 0.587474
},
{
"accuracy": 0.69403,
"f1": 0.686249,
"f1_weighted": 0.686249,
"ap": 0.651971,
"ap_weighted": 0.651971
},
{
"accuracy": 0.64827,
"f1": 0.639899,
"f1_weighted": 0.639899,
"ap": 0.590982,
"ap_weighted": 0.590982
},
{
"accuracy": 0.648118,
"f1": 0.648092,
"f1_weighted": 0.648092,
"ap": 0.596377,
"ap_weighted": 0.596377
}
],
"main_score": 0.665804,
"hf_subset": "default",
"languages": [
"eng-Latn"
]
}
]
},
"evaluation_time": 251.4205629825592,
"kg_co2_emissions": null
}
73 changes: 73 additions & 0 deletions ...7m-multilingual/47db56afe692f731540413c67dd818ff492277e7/AmazonReviewsClassification.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,73 @@
{
"dataset_revision": "1399c76144fd37290681b995c656ef9b2e06e26d",
"task_name": "AmazonReviewsClassification",
"mteb_version": "1.24.0",
"scores": {
"test": [
{
"accuracy": 0.36412,
"f1": 0.356332,
"f1_weighted": 0.356332,
"scores_per_experiment": [
{
"accuracy": 0.3758,
"f1": 0.369187,
"f1_weighted": 0.369187
},
{
"accuracy": 0.3832,
"f1": 0.368362,
"f1_weighted": 0.368362
},
{
"accuracy": 0.3608,
"f1": 0.356184,
"f1_weighted": 0.356184
},
{
"accuracy": 0.3442,
"f1": 0.339881,
"f1_weighted": 0.339881
},
{
"accuracy": 0.3884,
"f1": 0.373413,
"f1_weighted": 0.373413
},
{
"accuracy": 0.3656,
"f1": 0.355683,
"f1_weighted": 0.355683
},
{
"accuracy": 0.3194,
"f1": 0.316842,
"f1_weighted": 0.316842
},
{
"accuracy": 0.382,
"f1": 0.381975,
"f1_weighted": 0.381975
},
{
"accuracy": 0.3752,
"f1": 0.366611,
"f1_weighted": 0.366611
},
{
"accuracy": 0.3466,
"f1": 0.335187,
"f1_weighted": 0.335187
}
],
"main_score": 0.36412,
"hf_subset": "en",
"languages": [
"eng-Latn"
]
}
]
},
"evaluation_time": 4.899948358535767,
"kg_co2_emissions": null
}
Loading