SamLowe commited on
Commit
e16a586
·
1 Parent(s): a9958e8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -1
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 |