Update README.md
Browse files
README.md
CHANGED
@@ -1,5 +1,21 @@
|
|
1 |
-
An mDeBERTa-v3 model
|
2 |
political actors, or criticism directed towards a political actor or their policies.
|
3 |
|
4 |
-
The model was
|
5 |
-
of .827.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
An mDeBERTa-v3 model fine-tuned on English Language News articles by the Executive Approval Project team. This model is trained to detect whether a sequence contains either conflict between
|
2 |
political actors, or criticism directed towards a political actor or their policies.
|
3 |
|
4 |
+
The model was tuned for 8 epochs and returned a test-set accuracy of .897 and a balanced accuracy (accounting for the imbalance in the test set, where ~.77 of sequences did not contain conflict)
|
5 |
+
of .827.
|
6 |
+
|
7 |
+
The training/tuning set consisted of 6500 sequences (paragraphs), and a 80/20 train/test split was utilized. Each text was coded 3 times using majority rule.
|
8 |
+
|
9 |
+
Cleanlab was utilized to judge label health and fix mislabeled texts, which made up fewer than 10% of all labels. Texts marked as mislabeled were manually verified by a human coder.
|
10 |
+
|
11 |
+
The following hyperparameters were used during tuning:
|
12 |
+
num_train_epochs=8
|
13 |
+
learning_rate=2e-5
|
14 |
+
per_device_train_batch_size=8
|
15 |
+
per_device_eval_batch_size=64
|
16 |
+
warmup_ratio=0.06
|
17 |
+
weight_decay=0.1
|
18 |
+
load_best_model_at_end=True
|
19 |
+
metric_for_best_model="f1_macro
|
20 |
+
|
21 |
+
|