Update README.md
Browse files
README.md
CHANGED
|
@@ -52,7 +52,6 @@ Using a fixed threshold of 0.5 to convert the scores to binary predictions for e
|
|
| 52 |
This is a multi-label, multi-class dataset, so each label is effectively a separate binary classification and metrics are better measured per label.
|
| 53 |
|
| 54 |
Optimising the threshold per label to optimise the F1 metric, the metrics (evaluated on the go_emotions test split) are:
|
| 55 |
-
|
| 56 |
| | f1 | precision | recall | support | threshold |
|
| 57 |
| -------------- | ----- | --------- | ------ | ------- | --------- |
|
| 58 |
| admiration | 0.540 | 0.463 | 0.649 | 504 | 0.20 |
|
|
|
|
| 52 |
This is a multi-label, multi-class dataset, so each label is effectively a separate binary classification and metrics are better measured per label.
|
| 53 |
|
| 54 |
Optimising the threshold per label to optimise the F1 metric, the metrics (evaluated on the go_emotions test split) are:
|
|
|
|
| 55 |
| | f1 | precision | recall | support | threshold |
|
| 56 |
| -------------- | ----- | --------- | ------ | ------- | --------- |
|
| 57 |
| admiration | 0.540 | 0.463 | 0.649 | 504 | 0.20 |
|