Ineeoluwa's picture
Publish tested model, reproducible data and inspectable demo
02ebb71 verified
Raw History Blame Contribute Delete
3.93 kB
{
"baseline": {
"accuracy": 0.16666666666666666,
"macro_f1": 0.047619047619047616,
"samples": 30,
"labels": [
"account",
"billing",
"cancellation",
"delivery",
"login",
"technical"
],
"confusion_matrix": [
[
0,
0,
0,
0,
5,
0
],
[
0,
0,
0,
0,
5,
0
],
[
0,
0,
0,
0,
5,
0
],
[
0,
0,
0,
0,
5,
0
],
[
0,
0,
0,
0,
5,
0
],
[
0,
0,
0,
0,
5,
0
]
],
"per_class": [
{
"label": "account",
"precision": 0,
"recall": 0.0,
"f1": 0,
"support": 5
},
{
"label": "billing",
"precision": 0,
"recall": 0.0,
"f1": 0,
"support": 5
},
{
"label": "cancellation",
"precision": 0,
"recall": 0.0,
"f1": 0,
"support": 5
},
{
"label": "delivery",
"precision": 0,
"recall": 0.0,
"f1": 0,
"support": 5
},
{
"label": "login",
"precision": 0.16666666666666666,
"recall": 1.0,
"f1": 0.2857142857142857,
"support": 5
},
{
"label": "technical",
"precision": 0,
"recall": 0.0,
"f1": 0,
"support": 5
}
],
"loss": 1.8211933612823485
},
"baseline_description": "Pretrained encoder with an untrained classification head",
"test": {
"accuracy": 0.5666666666666667,
"macro_f1": 0.51994301994302,
"samples": 30,
"labels": [
"account",
"billing",
"cancellation",
"delivery",
"login",
"technical"
],
"confusion_matrix": [
[
5,
0,
0,
0,
0,
0
],
[
0,
0,
5,
0,
0,
0
],
[
0,
0,
0,
5,
0,
0
],
[
0,
0,
0,
3,
0,
2
],
[
0,
0,
0,
0,
4,
1
],
[
0,
0,
0,
0,
0,
5
]
],
"per_class": [
{
"label": "account",
"precision": 1.0,
"recall": 1.0,
"f1": 1.0,
"support": 5
},
{
"label": "billing",
"precision": 0,
"recall": 0.0,
"f1": 0,
"support": 5
},
{
"label": "cancellation",
"precision": 0.0,
"recall": 0.0,
"f1": 0,
"support": 5
},
{
"label": "delivery",
"precision": 0.375,
"recall": 0.6,
"f1": 0.4615384615384615,
"support": 5
},
{
"label": "login",
"precision": 1.0,
"recall": 0.8,
"f1": 0.888888888888889,
"support": 5
},
{
"label": "technical",
"precision": 0.625,
"recall": 1.0,
"f1": 0.7692307692307693,
"support": 5
}
],
"loss": 1.6918883482615152
},
"best_epoch": 4,
"validation_macro_f1": 0.2664141414141414,
"trainable_parameters": 8966,
"total_parameters": 4395660,
"trainable_pct": 0.204,
"steps": 92,
"elapsed_seconds": 164.736,
"base_model": "google/bert_uncased_L-2_H-128_A-2",
"base_revision": "30b0a37ccaaa32f332884b96992754e246e48c5f",
"dataset_fingerprint": "452710ab0bf595050805180e10ff423b58723ae1f34c22153da411fd87cbd8dc",
"torch_version": "2.14.1+cpu",
"hardware": {
"device": "cpu",
"threads": 2,
"machine": "x86_64"
}
}