wu981526092
commited on
Commit
•
0d7b6f1
1
Parent(s):
5f7aa43
Update README.md
Browse files
README.md
CHANGED
@@ -18,21 +18,8 @@ The Sentence-Level Stereotype Classifier is a transformer-based model developed
|
|
18 |
|
19 |
## Model Architecture
|
20 |
|
21 |
-
The model is built using the pretrained model. It is fine-tuned on a custom dataset for the task of sentence-level stereotype classification. The model uses a Sentence Classification architecture, typically used for Text Classification tasks.
|
22 |
-
|
23 |
-
## Model Performance
|
24 |
-
|
25 |
-
| Metric | Value |
|
26 |
-
|------------------------|-------------------------|
|
27 |
-
| eval_loss | 0.49603304266929626 |
|
28 |
-
| eval_precision | 0.7144313872416078 |
|
29 |
-
| eval_recall | 0.7034186400261718 |
|
30 |
-
| eval_f1 | 0.6980022981890632 |
|
31 |
-
| eval_balanced accuracy | 0.7034186400261718 |
|
32 |
-
| eval_runtime | 177.7807 |
|
33 |
-
| eval_samples_per_second| 59.348 |
|
34 |
-
| eval_steps_per_second | 3.712 |
|
35 |
-
| epoch | 6.0 |
|
36 |
|
37 |
## Classes
|
38 |
|
|
|
18 |
|
19 |
## Model Architecture
|
20 |
|
21 |
+
The model is built using the pretrained Distilbert model. It is fine-tuned on a custom dataset for the task of sentence-level stereotype classification. The model uses a Sentence Classification architecture, typically used for Text Classification tasks.
|
22 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
|
24 |
## Classes
|
25 |
|