Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
@@ -0,0 +1,95 @@
{
"dataset_revision": "e8379541af4e31359cca9fbcf4b00f2671dba205",
"task_name": "AmazonCounterfactualClassification",
"mteb_version": "1.36.8",
"scores": {
"test": [
{
"accuracy": 0.654478,
"f1": 0.588995,
"f1_weighted": 0.688119,
"ap": 0.275536,
"ap_weighted": 0.275536,
"scores_per_experiment": [
{
"accuracy": 0.616418,
"f1": 0.549027,
"f1_weighted": 0.655187,
"ap": 0.242238,
"ap_weighted": 0.242238
},
{
"accuracy": 0.652239,
"f1": 0.586585,
"f1_weighted": 0.68691,
"ap": 0.271424,
"ap_weighted": 0.271424
},
{
"accuracy": 0.613433,
"f1": 0.56813,
"f1_weighted": 0.653307,
"ap": 0.273803,
"ap_weighted": 0.273803
},
{
"accuracy": 0.662687,
"f1": 0.5781,
"f1_weighted": 0.693138,
"ap": 0.253635,
"ap_weighted": 0.253635
},
{
"accuracy": 0.68209,
"f1": 0.605637,
"f1_weighted": 0.711375,
"ap": 0.279889,
"ap_weighted": 0.279889
},
{
"accuracy": 0.676119,
"f1": 0.592849,
"f1_weighted": 0.704976,
"ap": 0.265527,
"ap_weighted": 0.265527
},
{
"accuracy": 0.710448,
"f1": 0.632862,
"f1_weighted": 0.735638,
"ap": 0.303321,
"ap_weighted": 0.303321
},
{
"accuracy": 0.670149,
"f1": 0.608979,
"f1_weighted": 0.703158,
"ap": 0.294014,
"ap_weighted": 0.294014
},
{
"accuracy": 0.620896,
"f1": 0.576009,
"f1_weighted": 0.660017,
"ap": 0.280835,
"ap_weighted": 0.280835
},
{
"accuracy": 0.640299,
"f1": 0.591772,
"f1_weighted": 0.677481,
"ap": 0.290673,
"ap_weighted": 0.290673
}
],
"main_score": 0.654478,
"hf_subset": "en",
"languages": [
"eng-Latn"
]
}
]
},
"evaluation_time": 6.934959650039673,
"kg_co2_emissions": null
}
Original file line number Diff line number Diff line change
@@ -0,0 +1,95 @@
{
"dataset_revision": "e2d317d38cd51312af73b3d32a06d1a08b442046",
"task_name": "AmazonPolarityClassification",
"mteb_version": "1.36.8",
"scores": {
"test": [
{
"accuracy": 0.669297,
"f1": 0.666978,
"f1_weighted": 0.666978,
"ap": 0.617461,
"ap_weighted": 0.617461,
"scores_per_experiment": [
{
"accuracy": 0.67263,
"f1": 0.672483,
"f1_weighted": 0.672483,
"ap": 0.614904,
"ap_weighted": 0.614904
},
{
"accuracy": 0.666872,
"f1": 0.66615,
"f1_weighted": 0.66615,
"ap": 0.608912,
"ap_weighted": 0.608912
},
{
"accuracy": 0.679342,
"f1": 0.678503,
"f1_weighted": 0.678503,
"ap": 0.618853,
"ap_weighted": 0.618853
},
{
"accuracy": 0.677578,
"f1": 0.671302,
"f1_weighted": 0.671302,
"ap": 0.632364,
"ap_weighted": 0.632364
},
{
"accuracy": 0.702635,
"f1": 0.70239,
"f1_weighted": 0.70239,
"ap": 0.644877,
"ap_weighted": 0.644877
},
{
"accuracy": 0.709087,
"f1": 0.708001,
"f1_weighted": 0.708001,
"ap": 0.654337,
"ap_weighted": 0.654337
},
{
"accuracy": 0.659377,
"f1": 0.657118,
"f1_weighted": 0.657118,
"ap": 0.601542,
"ap_weighted": 0.601542
},
{
"accuracy": 0.70882,
"f1": 0.704695,
"f1_weighted": 0.704695,
"ap": 0.661513,
"ap_weighted": 0.661513
},
{
"accuracy": 0.617692,
"f1": 0.615535,
"f1_weighted": 0.615535,
"ap": 0.575139,
"ap_weighted": 0.575139
},
{
"accuracy": 0.598932,
"f1": 0.593598,
"f1_weighted": 0.593598,
"ap": 0.562163,
"ap_weighted": 0.562163
}
],
"main_score": 0.669297,
"hf_subset": "default",
"languages": [
"eng-Latn"
]
}
]
},
"evaluation_time": 447.5662610530853,
"kg_co2_emissions": null
}
Original file line number Diff line number Diff line change
@@ -0,0 +1,73 @@
{
"dataset_revision": "1399c76144fd37290681b995c656ef9b2e06e26d",
"task_name": "AmazonReviewsClassification",
"mteb_version": "1.36.8",
"scores": {
"test": [
{
"accuracy": 0.33274,
"f1": 0.330787,
"f1_weighted": 0.330787,
"scores_per_experiment": [
{
"accuracy": 0.335,
"f1": 0.334234,
"f1_weighted": 0.334234
},
{
"accuracy": 0.3362,
"f1": 0.338144,
"f1_weighted": 0.338144
},
{
"accuracy": 0.327,
"f1": 0.322692,
"f1_weighted": 0.322692
},
{
"accuracy": 0.3332,
"f1": 0.335472,
"f1_weighted": 0.335472
},
{
"accuracy": 0.3308,
"f1": 0.329265,
"f1_weighted": 0.329265
},
{
"accuracy": 0.3418,
"f1": 0.337586,
"f1_weighted": 0.337586
},
{
"accuracy": 0.3196,
"f1": 0.318114,
"f1_weighted": 0.318114
},
{
"accuracy": 0.346,
"f1": 0.346881,
"f1_weighted": 0.346881
},
{
"accuracy": 0.3448,
"f1": 0.334427,
"f1_weighted": 0.334427
},
{
"accuracy": 0.313,
"f1": 0.311053,
"f1_weighted": 0.311053
}
],
"main_score": 0.33274,
"hf_subset": "en",
"languages": [
"eng-Latn"
]
}
]
},
"evaluation_time": 12.235694885253906,
"kg_co2_emissions": null
}
Loading
Loading