christinacdl
commited on
Commit
•
2301aa2
1
Parent(s):
3d9997d
Update README.md
Browse files
README.md
CHANGED
@@ -4,9 +4,17 @@ tags:
|
|
4 |
- generated_from_trainer
|
5 |
metrics:
|
6 |
- accuracy
|
|
|
|
|
|
|
7 |
model-index:
|
8 |
- name: clickbait_binary_detection_DeBERTa
|
9 |
results: []
|
|
|
|
|
|
|
|
|
|
|
10 |
---
|
11 |
|
12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -21,6 +29,18 @@ It achieves the following results on the evaluation set:
|
|
21 |
- Micro F1: 0.9069
|
22 |
- Accuracy: 0.9069
|
23 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
## Model description
|
25 |
|
26 |
More information needed
|
@@ -70,4 +90,4 @@ The following hyperparameters were used during training:
|
|
70 |
- Transformers 4.27.1
|
71 |
- Pytorch 2.0.1+cu118
|
72 |
- Datasets 2.9.0
|
73 |
-
- Tokenizers 0.13.3
|
|
|
4 |
- generated_from_trainer
|
5 |
metrics:
|
6 |
- accuracy
|
7 |
+
- f1
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
model-index:
|
11 |
- name: clickbait_binary_detection_DeBERTa
|
12 |
results: []
|
13 |
+
datasets:
|
14 |
+
- christinacdl/clickbait_notclickbait_dataset
|
15 |
+
language:
|
16 |
+
- en
|
17 |
+
pipeline_tag: text-classification
|
18 |
---
|
19 |
|
20 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
29 |
- Micro F1: 0.9069
|
30 |
- Accuracy: 0.9069
|
31 |
|
32 |
+
Performance on test set:
|
33 |
+
|
34 |
+
- Accuracy: 0.911986301369863
|
35 |
+
- F1 score: 0.9053903329555788
|
36 |
+
- Precision: 0.9069346899004087
|
37 |
+
- Recall : 0.9039394560612273
|
38 |
+
- Matthews Correlation Coefficient: 0.8108686139956713
|
39 |
+
|
40 |
+
- Precision of each class: [0.92560647 0.88826291]
|
41 |
+
- Recall of each class: [0.93518519 0.87269373]
|
42 |
+
- F1 score of each class: [0.93037117 0.88040949]
|
43 |
+
|
44 |
## Model description
|
45 |
|
46 |
More information needed
|
|
|
90 |
- Transformers 4.27.1
|
91 |
- Pytorch 2.0.1+cu118
|
92 |
- Datasets 2.9.0
|
93 |
+
- Tokenizers 0.13.3
|