Update README.md
Browse files
README.md
CHANGED
@@ -16,7 +16,13 @@ datasets:
|
|
16 |
widget:
|
17 |
- text: >-
|
18 |
Olympic champion Kostas Kederis today left hospital ahead of his date with IOC inquisitors claiming his innocence and vowing.
|
19 |
-
example_title:
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
model-index:
|
21 |
- name: roberta-base_topic_classification_nyt_news
|
22 |
results:
|
@@ -29,30 +35,27 @@ model-index:
|
|
29 |
metrics:
|
30 |
- type: F1
|
31 |
name: F1
|
32 |
-
value: 0.
|
33 |
- type: accuracy
|
34 |
name: accuracy
|
35 |
-
value: 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
36 |
pipeline_tag: text-classification
|
37 |
---
|
38 |
|
39 |
# roberta-base_topic_classification_nyt_news
|
40 |
|
41 |
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the NYT News dataset (https://www.kaggle.com/datasets/aryansingh0909/nyt-articles-21m-2000-present).
|
42 |
-
It achieves the following results on the
|
43 |
-
-
|
44 |
-
-
|
45 |
-
-
|
46 |
-
-
|
47 |
-
- Recall: 0.9094
|
48 |
-
|
49 |
-
## Model description
|
50 |
-
|
51 |
-
More information needed
|
52 |
-
|
53 |
-
## Intended uses & limitations
|
54 |
-
|
55 |
-
More information needed
|
56 |
|
57 |
## Training data
|
58 |
Training data was classified as follow:
|
@@ -92,7 +95,7 @@ The following hyperparameters were used during training:
|
|
92 |
| 0.1239 | 4.0 | 81920 | 0.3981 | 0.9117 | 0.9113 | 0.9114 | 0.9117 |
|
93 |
| 0.1472 | 5.0 | 102400 | 0.4033 | 0.9137 | 0.9135 | 0.9134 | 0.9137 |
|
94 |
|
95 |
-
### Model
|
96 |
|
97 |
-|precision|recall|f1|support
|
98 |
-|-|-|-|-
|
|
|
16 |
widget:
|
17 |
- text: >-
|
18 |
Olympic champion Kostas Kederis today left hospital ahead of his date with IOC inquisitors claiming his innocence and vowing.
|
19 |
+
example_title: Sports
|
20 |
+
- text: >-
|
21 |
+
Although many individuals are doing fever checks to screen for Covid-19, many Covid-19 patients never have a fever.
|
22 |
+
example_title: Health and Wellness
|
23 |
+
- text: >-
|
24 |
+
Twelve myths about Russia's War in Ukraine exposed
|
25 |
+
example_title: Crime
|
26 |
model-index:
|
27 |
- name: roberta-base_topic_classification_nyt_news
|
28 |
results:
|
|
|
35 |
metrics:
|
36 |
- type: F1
|
37 |
name: F1
|
38 |
+
value: 0.91
|
39 |
- type: accuracy
|
40 |
name: accuracy
|
41 |
+
value: 0.91
|
42 |
+
- type: precision
|
43 |
+
name: precision
|
44 |
+
value: 0.91
|
45 |
+
- type: recall
|
46 |
+
name: recall
|
47 |
+
value: 0.91
|
48 |
pipeline_tag: text-classification
|
49 |
---
|
50 |
|
51 |
# roberta-base_topic_classification_nyt_news
|
52 |
|
53 |
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the NYT News dataset (https://www.kaggle.com/datasets/aryansingh0909/nyt-articles-21m-2000-present).
|
54 |
+
It achieves the following results on the test set of 51200 cases:
|
55 |
+
- Accuracy: 0.91
|
56 |
+
- F1: 0.91
|
57 |
+
- Precision: 0.91
|
58 |
+
- Recall: 0.91
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
59 |
|
60 |
## Training data
|
61 |
Training data was classified as follow:
|
|
|
95 |
| 0.1239 | 4.0 | 81920 | 0.3981 | 0.9117 | 0.9113 | 0.9114 | 0.9117 |
|
96 |
| 0.1472 | 5.0 | 102400 | 0.4033 | 0.9137 | 0.9135 | 0.9134 | 0.9137 |
|
97 |
|
98 |
+
### Model performance
|
99 |
|
100 |
-|precision|recall|f1|support
|
101 |
-|-|-|-|-
|