paulagarciaserrano
commited on
Commit
•
4922306
1
Parent(s):
76670d6
Update README.md
Browse files
README.md
CHANGED
@@ -1,10 +1,9 @@
|
|
1 |
-
This model is a fine-tuned version
|
2 |
|
3 |
-
|
4 |
-
* Macro F1-Score:
|
5 |
|
6 |
# Intended uses
|
7 |
-
This model is trained to classify the given text into one of the following classes: *moderate*, *severe
|
8 |
It corresponds to a **multiclass classification** task.
|
9 |
|
10 |
# Training and evaluation data
|
@@ -83,5 +82,6 @@ The following hyperparameters were used during training:
|
|
83 |
* per_device_train_batch_size: 8
|
84 |
* per_device_eval_batch_size: 8
|
85 |
* num_train_epochs: 5
|
|
|
86 |
* weight_decay: 0.01
|
87 |
-
* metric_for_best_model: macro
|
|
|
1 |
+
This model is a fine-tuned version the <a href="https://huggingface.co/cardiffnlp/twitter-roberta-base">cardiffnlp/twitter-roberta-base</a> model. It has been trained using a recently published corpus: <a href="https://competitions.codalab.org/competitions/36410#learn_the_details">Shared task on Detecting Signs of Depression from Social Media Text at LT-EDI 2022-ACL 2022</a>.
|
2 |
|
3 |
+
The obtained macro f1-score is 0.54, on the development set of the competition.
|
|
|
4 |
|
5 |
# Intended uses
|
6 |
+
This model is trained to classify the given text into one of the following classes: *moderate*, *severe*, or *not depressed*.
|
7 |
It corresponds to a **multiclass classification** task.
|
8 |
|
9 |
# Training and evaluation data
|
|
|
82 |
* per_device_train_batch_size: 8
|
83 |
* per_device_eval_batch_size: 8
|
84 |
* num_train_epochs: 5
|
85 |
+
* seed: 10
|
86 |
* weight_decay: 0.01
|
87 |
+
* metric_for_best_model: macro-f1
|